A
licenseA
qualityNot graded
maintenanceEnables interaction with ElevenLabs Text-to-Speech and audio processing APIs. Supports speech generation, voice cloning, audio transcription, and sound effect creation through natural language.
24
MIT
@aiwerk/mcp-server-elevenlabs
by AIWerk
Provides tools for interacting with the ElevenLabs API, covering 390 operations across text-to-speech, speech-to-text, voice cloning, dubbing, audio isolation, knowledge base, and other documented endpoints. Supports file uploads, raw audio/byte downloads, dry-run mode, domain filtering, and credit-aware operation metadata.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@aiwerk/mcp-server-elevenlabs turn this text into speech with Rachel's voice and save it as intro.mp3"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@aiwerk/mcp-server-elevenlabs
An MCP server for the ElevenLabs API. 390 tools, generated from the live OpenAPI document, covering every documented endpoint.
Why this exists
ElevenLabs ships its own MCP server. It is hosted, it authenticates with OAuth, and it exposes about a dozen high-level tools for managing ElevenAgents plus one text to speech call. That is a good fit for "create a support agent and set its voice".
This one is for the rest of the API. The whole of it:
Tools | |
ElevenLabs REST API (OpenAPI, live) | 390 operations |
Official hosted MCP server | ~12 |
Official local server (archived 2026-08) | 27 |
This server | 390 |
It also handles the two things a generated client usually gets wrong: 31 endpoints take file uploads (speech to text, voice cloning, dubbing, audio isolation, knowledge base) and 21 return raw bytes (all the text to speech variants). Parsing audio as JSON produces a plausible-looking string of mojibake, so those paths are written by hand and tested.
What the official hosted server does better: OAuth means no API key is copied into the client, and its agent tools are composed product logic rather than raw endpoints ("what would this agent cost per conversation on a different model" is not one API call). Use both if that is what you need. They do not conflict.
Related MCP server: ElevenLabs MCP Server
Install
npm install -g @aiwerk/mcp-server-elevenlabsOr run it straight from npx in a client config:
{
"mcpServers": {
"elevenlabs": {
"command": "npx",
"args": ["-y", "@aiwerk/mcp-server-elevenlabs"],
"env": {
"ELEVENLABS_API_KEY": "your-key",
"ELEVENLABS_OUTPUT_DIR": "/where/audio/should/land"
}
}
}
}Get a key at https://elevenlabs.io/app/settings/api-keys. The free tier includes 10k credits a month.
Keeping the key out of the config
An MCP client config is a plain file that tends to live in a repo or a dotfile, so a
key written into its env block is a key in cleartext. If you keep secrets in a
password manager, start the server through a small wrapper instead:
#!/usr/bin/env bash
set -euo pipefail
ELEVENLABS_API_KEY="$(pass show api/elevenlabs | head -1)" # or your own manager
export ELEVENLABS_API_KEY
exec npx -y @aiwerk/mcp-server-elevenlabs@0.1.1 "$@"{
"mcpServers": {
"elevenlabs": {
"command": "/path/to/the/wrapper",
"env": { "ELEVENLABS_OUTPUT_DIR": "/where/audio/should/land" }
}
}
}The secret is read at start-up and handed to the process as its own environment
variable, so it never appears in argv where other users on the machine could read
it. Note the pinned version: a bare npx -y <package> resolves to whatever is newest
at that moment, which is how an update lands in the middle of a production run.
Configuration
Variable | Default | Purpose |
| required | Sent as the |
| unset | Where generated audio lands. Without it, small results come back inline as base64 and large ones error. |
| all | Comma-separated domains, e.g. |
|
|
|
|
|
|
|
| Generation is slow; a dubbing job outlives a CRUD timeout. |
|
| Above this, a binary result needs somewhere to be written. |
|
| Guards against reading an enormous file into memory. |
|
| Longest 429 backoff to sit through before failing. |
|
| Point at a data-residency region if your workspace is in one. |
Files in and out
Uploads. Every binary field is offered two ways:
// local install: the server can read your disk
{ "file_path": "/home/me/interview.mp3", "model_id": "scribe_v1" }
// containerised or remote: send the bytes
{ "file_base64": "SUQzB...", "file_filename": "interview.mp3", "model_id": "scribe_v1" }Fields that accept several files (add_voice, create_finetune,
add_pvc_voice_samples) use files_paths / files_base64_list / files_filenames.
Downloads. Anything returning audio, video or a zip takes output_path:
{ "voice_id": "...", "text": "Guten Tag", "output_path": "greeting.mp3" }
// → { "contentType": "audio/mpeg", "bytes": 26375, "path": "/output/dir/greeting.mp3" }A relative path resolves against ELEVENLABS_OUTPUT_DIR. With no path and no output
dir, the audio comes back as an MCP audio block, as long as it is under the inline
limit. Base64 inflates by a third and every byte crosses the model's context, so
prefer a file for anything longer than a sentence.
Credits and safety
66 operations spend credits, and each one says so in its description. Nothing here guesses on your behalf:
ELEVENLABS_DRY_RUN=1blocks every write and generation call.Only
GETis marked read-only. Several POSTs merely query, but every one of them also bills, so they are gated with the writes.DELETEoperations carrydestructiveHint.
An ElevenLabs key can be restricted per endpoint group, given its own credit quota and locked to an IP range. All three failures arrive as HTTP 401, and this server tells them apart, so "out of credits", "this key may not touch this endpoint" and "this host is not on the allowlist" do not all read as "check your credentials".
Regenerating from the spec
The spec is committed, not fetched at build time, so a vendor edit cannot land in a release nobody reviewed.
npm run fetch-spec # writes spec/elevenlabs-openapi.json, reports whether it changed
npm run regen # naming table + generated tools
npm testDevelopment
npm install
npm run build
npm test # 47 unit tests
npm run smoke # live test against the real API, spends a few creditsThe smoke test does a round trip that the unit tests cannot: it generates speech to a file, then uploads that same file back to speech-to-text and checks the words come out again.
License
MIT. Not affiliated with ElevenLabs.
Available Tools
390 toolsadd_chapterC
Create Chapter Spends ElevenLabs credits.
Inputs: name (required), project_id (required), from_url.
add_documentation_to_knowledge_baseC
Add To Knowledge Base Deprecated upstream.
Inputs: url, name, agent_id, file_path, +2 more.
add_from_fileC
Add A Pronunciation Dictionary
Inputs: name (required), file_path, description, file_base64, +2 more.
add_from_rulesC
Add A Pronunciation Dictionary
Inputs: name (required), rules (required), description, workspace_access.
add_languageC
Add A Language To The Resource Spends ElevenLabs credits. Deprecated upstream.
Inputs: language (required), dubbing_id (required).
add_mcp_server_tool_approval_routeC
Create Mcp Server Tool Approval
Inputs: tool_name (required), mcp_server_id (required), tool_description (required), input_schema, +1 more.
add_mcp_tool_config_override_routeD
Create Mcp Tool Configuration Override
Inputs: tool_name (required), mcp_server_id (required), assignments, environment, +10 more.
add_memberC
Add Member To User Group
Inputs: email (required), group_id (required).
add_projectB
Create Studio Project Spends ElevenLabs credits.
Inputs: name (required), title, author, genres, +27 more.
add_pvc_voice_samplesC
Add Samples To Pvc Voice
Inputs: voice_id (required), files_paths, files_filenames, files_base64_list, +1 more.
add_rulesC
Add Rules To The Pronunciation Dictionary
Inputs: rules (required), pronunciation_dictionary_id (required).
add_sharing_voiceD
Add Shared Voice
Inputs: new_name (required), voice_id (required), public_user_id (required), bookmarked.
add_ticket_comment_routeC
Add Comment To Agent Conversation Ticket
Inputs: comment (required), agentqa_ticket_id (required).
add_tool_routeD
Add Tool
Inputs: tool_config (required), response_mocks.
add_turn_comment_routeC
Add Turn Comment To Agent Conversation Ticket
Inputs: comment (required), turn_index (required), agentqa_ticket_id (required).
add_voiceD
Add Voice
Inputs: name (required), labels, description, files_paths, +3 more.
agent_testing_bulk_move_routeC
Bulk Move Tests To Folder
Inputs: entity_ids (required), move_to.
assign_conversation_tags_routeD
Assign Conversation Tags
Inputs: tag_ids (required), conversation_id (required).
audio_isolationB
Audio Isolation Spends ElevenLabs credits. Returns audio/mpeg bytes; pass output_path to save them.
Inputs: audio_path, file_format, output_path, preview_b64, +2 more.
audio_isolation_streamB
Audio Isolation Stream Spends ElevenLabs credits. Returns audio/mpeg bytes; pass output_path to save them.
Inputs: audio_path, file_format, output_path, audio_base64, +1 more.
audio_native_project_update_content_endpointC
Update Audio-Native Project Content
Inputs: project_id (required), file_path, file_base64, auto_convert, +2 more.
audio_native_update_content_from_urlC
Update Audio-Native Content From Url
Inputs: url (required), title, author.
cancel_batch_callC
Cancel A Batch Call.
Inputs: batch_id (required).
cancel_crawl_job_routeC
Cancel Crawl Job
Inputs: crawl_job_id (required).
cancel_file_upload_routeCDestructiveIdempotent
Delete File Upload
Inputs: file_id (required), conversation_id (required).
compile_procedures_routeC
Compile Procedures
Inputs: agent_id (required), branch_id (required).
compose_detailedC
Compose Music With A Detailed Response Spends ElevenLabs credits.
Inputs: seed, prompt, model_id, finetune_id, +15 more.
compose_detailed_streamC
Stream Composed Music With A Detailed Response Spends ElevenLabs credits.
Inputs: seed, prompt, model_id, finetune_id, +12 more.
compose_planC
Generate Composition Plan Spends ElevenLabs credits.
Inputs: prompt (required), model_id, music_length_ms, source_composition_plan.
convert_chapter_endpointB
Convert Chapter Spends ElevenLabs credits.
Inputs: chapter_id (required), project_id (required).
convert_project_endpointC
Convert Studio Project Spends ElevenLabs credits.
Inputs: project_id (required).
create_agent_conversation_ticket_routeC
Create Agent Conversation Ticket
Inputs: conversation_id (required), qa_comment, turn_comments.
create_agent_deployment_routeC
Create Or Update Deployments
Inputs: agent_id (required), deployment_request (required).
create_agent_draft_routeD
Create Agent Draft
Inputs: name (required), agent_id (required), workflow (required), branch_id (required), +3 more.
create_agent_response_test_routeD
Create Agent Response Test
Inputs: name, type, environment, chat_history, +17 more.
create_agent_routeD
Create Agent
Inputs: conversation_config (required), name, tags, workflow, +2 more.
create_agent_test_folder_routeC
Create Agent Test Folder
Inputs: name (required), parent_folder_id.
create_audio_native_projectD
Creates Audio Native Enabled Project.
Inputs: name (required), image, small, title, +12 more.
create_auth_connectionD
Create Workspace Auth Connection
Inputs: name, token, issuer, key_id, +22 more.
create_batch_callC
Submit A Batch Call Request.
Inputs: agent_id (required), call_name (required), recipients (required), timezone, +7 more.
create_branch_routeC
Create A New Branch
Inputs: name (required), agent_id (required), description (required), parent_version_id (required), +4 more.
create_clipB
Create A Segment For The Speaker Spends ElevenLabs credits. Deprecated upstream.
Inputs: end_time (required), dubbing_id (required), speaker_id (required), start_time (required), +2 more.
create_conversation_tag_routeC
Create Conversation Tag
Inputs: title (required), description.
create_crawl_job_routeD
Create Crawl Job
Inputs: url (required), pattern, max_depth, max_pages, +5 more.
create_dubbingC
Dub A Video Or An Audio File Spends ElevenLabs credits.
Inputs: mode, name, csv_fps, end_time, +24 more.
create_environment_variableD
Create Environment Variable
Inputs: type, label, values.
create_file_document_routeC
Create File Document
Inputs: name, file_path, file_base64, file_filename, +1 more.
create_finetuneB
Create Music Finetune Spends ElevenLabs credits.
Inputs: name (required), primary_genre (required), tags, model_id, +4 more.
create_folder_routeD
Create Folder
Inputs: name (required), auto_remove, enable_auto_sync, parent_folder_id, +1 more.
create_image_generationD
Create Image Generation
Inputs: mask, seed, images, prompt, +6 more.
create_manual_agent_ticket_routeD
Create Manual Agent Ticket
Inputs: agent_id (required), qa_comment (required).
create_mcp_server_routeC
Create Mcp Server
Inputs: config (required).
create_phone_number_routeD
Import Phone Number
Inputs: sid, label, token, app_id, +15 more.
create_podcastC
Create Podcast Spends ElevenLabs credits.
Inputs: mode (required), source (required), model_id (required), intro, +9 more.
create_procedure_routeD
Create Procedure
Inputs: agent_id (required), branch_id (required), name, type, +3 more.
create_pvc_voiceD
Create Pvc Voice
Inputs: name (required), language (required), labels, description.
create_secret_routeC
Create Convai Workspace Secret
Inputs: name (required), type (required), value (required).
create_service_accountD
Create Service Account
Inputs: name (required), default_sharing_groups.
create_service_account_api_keyD
Create Service Account Api Key
Inputs: name (required), permissions (required), service_account_user_id (required), allowed_ips, +2 more.
create_speakerC
Create A New Speaker Spends ElevenLabs credits. Deprecated upstream.
Inputs: dubbing_id (required), voice_id, voice_style, speaker_name, +2 more.
create_speech_engineD
Create Speech Engine
Inputs: speech_engine (required), asr, tts, vad, +8 more.
create_text_document_routeD
Create Text Document
Inputs: text (required), name, parent_folder_id.
create_text_to_speech_generationD
Create Speech Generation
Inputs: text, voice, webhook, model_id, +4 more.
create_url_document_routeD
Create Url Document
Inputs: url (required), name, auto_remove, enable_auto_sync, +2 more.
create_video_generationD
Create Video Generation
Inputs: seed, audio, image, audios, +15 more.
create_voiceB
Create A New Voice From Voice Preview Spends ElevenLabs credits.
Inputs: voice_name (required), voice_description (required), generated_voice_id (required), labels, +1 more.
create_workspace_webhook_routeC
Create Workspace Webhook
Inputs: settings (required).
delete_agent_conversation_ticket_routeCDestructiveIdempotent
Delete Agent Conversation Ticket
Inputs: agentqa_ticket_id (required).
delete_agent_draft_routeCDestructiveIdempotent
Delete Agent Draft
Inputs: agent_id (required), branch_id (required).
delete_agent_hold_audio_routeCDestructiveIdempotent
Delete Agent Hold Audio
Inputs: agent_id (required).
delete_agent_routeCDestructiveIdempotent
Delete Agent
Inputs: agent_id (required).
delete_agent_test_folder_routeCDestructiveIdempotent
Delete Agent Test Folder
Inputs: folder_id (required), force.
delete_asset_endpointCDestructiveIdempotent
Delete Asset
Inputs: asset_id (required).
delete_audio_isolation_history_itemCDestructiveIdempotent
Delete Audio Isolation History Item
Inputs: history_item_id (required).
delete_auth_connectionCDestructiveIdempotent
Delete Workspace Auth Connection
Inputs: auth_connection_id (required).
delete_batch_callCDestructiveIdempotent
Delete A Batch Call.
Inputs: batch_id (required).
delete_chapter_endpointCDestructiveIdempotent
Delete Chapter
Inputs: chapter_id (required), project_id (required).
delete_chat_response_test_routeCDestructiveIdempotent
Delete Agent Response Test
Inputs: test_id (required).
delete_conversation_routeCDestructiveIdempotent
Delete Conversation
Inputs: conversation_id (required).
delete_conversation_tag_routeCDestructiveIdempotent
Delete Conversation Tag
Inputs: tag_id (required).
delete_dubbingCDestructiveIdempotent
Delete Dubbing
Inputs: dubbing_id (required).
delete_finetuneCDestructiveIdempotent
Delete Music Finetune
Inputs: finetune_id (required).
delete_inviteCDestructiveIdempotent
Delete Existing Invitation
Inputs: email (required).
delete_knowledge_base_documentCDestructiveIdempotent
Delete Knowledge Base Document Or Folder
Inputs: documentation_id (required), force.
delete_mcp_server_routeCDestructiveIdempotent
Delete Mcp Server
Inputs: mcp_server_id (required).
delete_phone_number_routeCDestructiveIdempotent
Delete Phone Number
Inputs: phone_number_id (required).
delete_procedure_draft_routeCDestructiveIdempotent
Delete Procedure Draft
Inputs: agent_id (required), branch_id (required), procedure_id (required).
delete_projectCDestructiveIdempotent
Delete Studio Project
Inputs: project_id (required).
delete_pvc_voice_sampleCDestructiveIdempotent
Delete Pvc Voice Sample
Inputs: voice_id (required), sample_id (required).
delete_rag_indexCDestructiveIdempotent
Delete Rag Index.
Inputs: rag_index_id (required), documentation_id (required).
delete_sampleCDestructiveIdempotent
Delete Sample
Inputs: voice_id (required), sample_id (required).
delete_secret_routeCDestructiveIdempotent
Delete Convai Workspace Secret
Inputs: secret_id (required).
delete_segmentCDestructiveIdempotent
Deletes A Single Segment Deprecated upstream.
Inputs: dubbing_id (required), segment_id (required).
delete_service_account_api_keyCDestructiveIdempotent
Delete Service Account Api Key
Inputs: api_key_id (required), service_account_user_id (required).
delete_speech_engineCDestructiveIdempotent
Delete Speech Engine
Inputs: speech_engine_id (required).
delete_speech_history_itemCDestructiveIdempotent
Delete History Item
Inputs: history_item_id (required).
delete_tool_routeCDestructiveIdempotent
Delete Tool
Inputs: tool_id (required), force.
delete_transcript_by_idCDestructiveIdempotent
Delete Transcript By Id
Inputs: transcription_id (required).
delete_voiceDDestructiveIdempotent
Delete Voice
Inputs: voice_id (required).
delete_whatsapp_accountCDestructiveIdempotent
Delete Whatsapp Account
Inputs: phone_number_id (required).
delete_workspace_webhook_routeCDestructiveIdempotent
Delete Workspace Webhook
Inputs: webhook_id (required).
disableC
Disable Api Key
Inputs: api_key_name (required).
download_speech_history_itemsB
Download History Items Returns application/zip bytes; pass output_path to save them.
Inputs: history_item_ids (required), output_path, output_format.
dubB
Dubs All Or Some Segments And Languages Spends ElevenLabs credits. Deprecated upstream.
Inputs: segments (required), languages (required), dubbing_id (required).
dubbing_language_createC
Create Dubbing Language Target Spends ElevenLabs credits.
Inputs: project_id (required), target_language (required), translations, voice_settings.
dubbing_language_deleteCDestructiveIdempotent
Delete Dubbing Language Target
Inputs: project_id (required), language_id (required).
dubbing_language_getCRead-onlyIdempotent
Get Dubbing Language Target
Inputs: project_id (required), language_id (required).
dubbing_language_listCRead-onlyIdempotent
List Dubbing Language Targets
Inputs: project_id (required), cursor, status, page_size.
dubbing_project_createB
Create Dubbing Project Spends ElevenLabs credits.
Inputs: keyterms, model_id, file_path, reference, +9 more.
dubbing_project_deleteCDestructiveIdempotent
Delete Dubbing Project
Inputs: project_id (required).
dubbing_project_getCRead-onlyIdempotent
Get Dubbing Project
Inputs: project_id (required).
dubbing_project_listCRead-onlyIdempotent
List Dubbing Projects
Inputs: cursor, status, page_size, sort_direction.
dubbing_target_transcript_getCRead-onlyIdempotent
Get Dubbing Target Transcript
Inputs: project_id (required), language_id (required).
dubbing_target_transcript_regenerateB
Regenerate Dubbing Target Spends ElevenLabs credits.
Inputs: project_id (required), language_id (required).
dubbing_target_transcript_segments_updateC
Update Dubbing Target Transcript Segments Spends ElevenLabs credits.
Inputs: segments (required), project_id (required), language_id (required).
dubbing_target_transcript_segment_updateC
Update Dubbing Target Transcript Segment Spends ElevenLabs credits.
Inputs: project_id (required), segment_id (required), language_id (required), translation.
dubbing_transcript_getCRead-onlyIdempotent
Get Dubbing Transcript
Inputs: project_id (required).
dubbing_transcript_segment_addB
Add Dubbing Transcript Segment Spends ElevenLabs credits.
Inputs: text (required), end_s (required), start_s (required), project_id (required), +1 more.
dubbing_transcript_segment_deleteCDestructiveIdempotent
Delete Dubbing Transcript Segment
Inputs: project_id (required), segment_id (required).
dubbing_transcript_segments_updateC
Update Dubbing Transcript Segments Spends ElevenLabs credits.
Inputs: segments (required), project_id (required).
dubbing_transcript_segment_updateC
Update Dubbing Transcript Segment Spends ElevenLabs credits.
Inputs: project_id (required), segment_id (required), text, end_s, +2 more.
duplicate_agent_routeC
Duplicate Agent
Inputs: agent_id (required), name.
edit_chapterC
Update Chapter Spends ElevenLabs credits.
Inputs: chapter_id (required), project_id (required), name, content.
edit_projectC
Update Studio Project Spends ElevenLabs credits.
Inputs: name (required), project_id (required), default_title_voice_id (required), default_paragraph_voice_id (required), +4 more.
edit_project_contentC
Update Studio Project Content Spends ElevenLabs credits.
Inputs: project_id (required), from_url, auto_convert, from_content_json, +3 more.
edit_pvc_voiceD
Edit Pvc Voice
Inputs: voice_id (required), name, labels, language, +1 more.
edit_pvc_voice_sampleD
Update Pvc Voice Sample
Inputs: voice_id (required), sample_id (required), file_name, trim_end_time, +3 more.
edit_service_account_api_keyD
Edit Service Account Api Key
Inputs: api_key_id (required), service_account_user_id (required), name, is_enabled, +4 more.
edit_voiceD
Edit Voice
Inputs: name (required), voice_id (required), labels, description, +5 more.
edit_voice_settingsD
Edit Voice Settings
Inputs: voice_id (required), speed, style, stability, +2 more.
edit_workspace_webhook_routeD
Update Workspace Webhook
Inputs: name (required), webhook_id (required), is_disabled (required), events, +2 more.
export_batch_callCRead-onlyIdempotent
Export Batch Call Results
Inputs: batch_id (required).
forced_alignmentC
Create Forced Alignment Spends ElevenLabs credits.
Inputs: text (required), file_path, file_base64, file_filename.
generateC
Compose Music Spends ElevenLabs credits. Returns audio/* bytes; pass output_path to save them.
Inputs: seed, prompt, model_id, finetune_id, +13 more.
get_agent_conversation_ticket_routeCRead-onlyIdempotent
Get Agent Conversation Ticket
Inputs: agentqa_ticket_id (required).
get_agent_knowledge_base_sizeCRead-onlyIdempotent
Returns The Size Of The Agent'S Knowledge Base
Inputs: agent_id (required).
get_agent_knowledge_base_summaries_routeCRead-onlyIdempotent
Get Knowledge Base Summaries By Ids
Inputs: document_ids (required).
get_agent_link_routeCRead-onlyIdempotent
Get Shareable Agent Link
Inputs: agent_id (required).
get_agent_llm_expected_cost_calculationC
Calculate Expected Llm Usage For An Agent
Inputs: agent_id (required), rag_enabled, prompt_length, number_of_pages.
get_agent_response_test_routeCRead-onlyIdempotent
Get Agent Response Test By Id
Inputs: test_id (required).
get_agent_response_tests_summaries_routeC
Get Agent Response Test Summaries By Ids
Inputs: test_ids (required).
get_agent_routeCRead-onlyIdempotent
Get Agent
Inputs: agent_id (required), branch_id, version_id.
get_agents_routeCRead-onlyIdempotent
List Agents
Inputs: tags, cursor, search, sort_by, +5 more.
get_agent_summaries_routeCRead-onlyIdempotent
Get Agent Summaries
Inputs: agent_ids (required).
get_agent_test_folder_routeCRead-onlyIdempotent
Get Agent Test Folder By Id
Inputs: folder_id (required).
get_agent_topics_routeCRead-onlyIdempotent
Get Agent Conversation Topics
Inputs: agent_id (required), cursor, sort_by, page_size, +4 more.
get_agent_widget_routeCRead-onlyIdempotent
Get Agent Widget Config
Inputs: agent_id (required), conversation_signature.
get_assetCRead-onlyIdempotent
Get Asset
Inputs: asset_id (required).
get_assignable_users_routeCRead-onlyIdempotent
Get Agent Conversation Ticket Assignable Users
Inputs: agent_id (required).
get_audio_from_sampleCRead-onlyIdempotent
Get Audio From Sample Returns audio/* bytes; pass output_path to save them.
Inputs: voice_id (required), sample_id (required), output_path.
get_audio_full_from_speech_history_itemBRead-onlyIdempotent
Get Audio From History Item Returns audio/mpeg bytes; pass output_path to save them.
Inputs: history_item_id (required), output_path.
get_audio_isolation_historyBRead-onlyIdempotent
Get Audio Isolation History
Inputs: page, search, page_size.
get_audio_native_project_settings_endpointCRead-onlyIdempotent
Get Audio Native Project Settings
Inputs: project_id (required).
get_batch_callCRead-onlyIdempotent
Get A Batch Call By Id.
Inputs: batch_id (required).
get_branches_routeCRead-onlyIdempotent
List Agent Branches
Inputs: agent_id (required), limit, include_archived, include_commit_status.
get_branch_routeCRead-onlyIdempotent
Get Agent Branch
Inputs: agent_id (required), branch_id (required).
get_chapter_by_id_endpointCRead-onlyIdempotent
Get Chapter
Inputs: chapter_id (required), project_id (required).
get_chaptersCRead-onlyIdempotent
List Chapters
Inputs: project_id (required).
get_chapter_snapshot_endpointCRead-onlyIdempotent
Get Chapter Snapshot
Inputs: chapter_id (required), project_id (required), chapter_snapshot_id (required).
get_chapter_snapshotsCRead-onlyIdempotent
List Chapter Snapshots
Inputs: chapter_id (required), project_id (required).
get_conversation_audio_routeBRead-onlyIdempotent
Get Conversation Audio Returns audio/mpeg bytes; pass output_path to save them.
Inputs: conversation_id (required), output_path.
get_conversation_histories_routeCRead-onlyIdempotent
Get Conversations
Inputs: cursor, search, tag_ids, user_id, +37 more.
get_conversation_history_routeCRead-onlyIdempotent
Get Conversation Details
Inputs: conversation_id (required), format.
get_conversation_signed_linkCRead-onlyIdempotent
Get Signed Url
Inputs: agent_id (required), branch_id, version_id, environment, +2 more.
get_conversation_sip_messagesCRead-onlyIdempotent
Get Sip Messages For A Conversation
Inputs: conversation_id (required), cursor, page_size.
get_conversation_summary_routeCRead-onlyIdempotent
Get Conversation Summary
Inputs: conversation_id (required), max_messages.
get_conversation_tag_routeCRead-onlyIdempotent
Get Conversation Tag
Inputs: tag_id (required).
get_conversation_users_routeCRead-onlyIdempotent
Get Conversation Users
Inputs: cursor, search, sort_by, agent_id, +5 more.
get_crawl_job_routeCRead-onlyIdempotent
Get Crawl Job Details
Inputs: crawl_job_id (required).
get_dashboard_settings_routeBRead-onlyIdempotent
Get Convai Dashboard Settings
Inputs: no named parameters.
get_documentation_chunk_from_knowledge_baseCRead-onlyIdempotent
Get Documentation Chunk From Knowledge Base
Inputs: chunk_id (required), documentation_id (required), embedding_model.
get_documentation_chunks_from_knowledge_baseCRead-onlyIdempotent
Get All Rag Chunks For A Document
Inputs: embedding_model (required), documentation_id (required), cursor, page_size.
get_documentation_from_knowledge_baseCRead-onlyIdempotent
Get Documentation From Knowledge Base
Inputs: documentation_id (required), agent_id.
get_dubbed_fileBRead-onlyIdempotent
Get Dubbed File Returns audio/mpeg bytes; pass output_path to save them.
Inputs: dubbing_id (required), language_code (required), output_path.
get_dubbed_metadataCRead-onlyIdempotent
Get Dubbing
Inputs: dubbing_id (required).
get_dubbed_transcript_fileCRead-onlyIdempotent
Get Dubbed Transcript Deprecated upstream.
Inputs: dubbing_id (required), language_code (required), format_type.
get_dubbing_resourceBRead-onlyIdempotent
Get The Dubbing Resource For An Id. Deprecated upstream.
Inputs: dubbing_id (required).
get_dubbing_transcriptsCRead-onlyIdempotent
Retrieve A Transcript
Inputs: dubbing_id (required), format_type (required), language_code (required).
get_environment_variableCRead-onlyIdempotent
Get Environment Variable
Inputs: env_var_id (required).
get_finetuneCRead-onlyIdempotent
Get Music Finetune
Inputs: finetune_id (required).
get_finetunesCRead-onlyIdempotent
Get Music Finetunes
Inputs: sort, cursor, page_size, created_by, +2 more.
get_groups_endpointCRead-onlyIdempotent
Get All Groups
Inputs: no named parameters.
get_image_generationCRead-onlyIdempotent
Get Image Generation
Inputs: generation_id (required).
get_knowledge_base_bulk_dependent_agents_routeC
Get Dependent Agents For Multiple Documents
Inputs: document_ids (required), cursor, page_size, dependent_type.
get_knowledge_base_contentCRead-onlyIdempotent
Get Document Content
Inputs: documentation_id (required).
get_knowledge_base_dependent_agentsCRead-onlyIdempotent
Get Dependent Agents List
Inputs: documentation_id (required), cursor, page_size, dependent_type.
get_knowledge_base_list_routeDRead-onlyIdempotent
Get Knowledge Base List
Inputs: types, cursor, search, sort_by, +7 more.
get_knowledge_base_source_file_urlCRead-onlyIdempotent
Get Document Source File Url
Inputs: documentation_id (required).
get_library_voicesCRead-onlyIdempotent
Get Voices
Inputs: age, page, sort, accent, +14 more.
get_live_countCRead-onlyIdempotent
Get Live Count
Inputs: agent_id, agent_ids.
get_livekit_tokenCRead-onlyIdempotent
Get Webrtc Token
Inputs: agent_id (required), branch_id, version_id, environment, +2 more.
get_mcp_routeCRead-onlyIdempotent
Get Mcp Server
Inputs: mcp_server_id (required).
get_mcp_tool_config_override_routeCRead-onlyIdempotent
Get Mcp Tool Configuration Override
Inputs: tool_name (required), mcp_server_id (required).
get_modelsCRead-onlyIdempotent
Get Models
Inputs: no named parameters.
get_or_create_rag_indexesC
Compute Rag Indexes In Batch
Inputs: items (required).
get_phone_number_routeCRead-onlyIdempotent
Get Phone Number
Inputs: phone_number_id (required).
get_procedure_draft_routeCRead-onlyIdempotent
Get Procedure Draft
Inputs: agent_id (required), branch_id (required), procedure_id (required).
get_procedure_routeDRead-onlyIdempotent
Get Procedure
Inputs: agent_id (required), branch_id (required), procedure_id (required), version_id, +1 more.
get_project_by_idCRead-onlyIdempotent
Get Studio Project
Inputs: project_id (required), share_id.
get_project_muted_tracks_endpointCRead-onlyIdempotent
Get Project Muted Tracks
Inputs: project_id (required).
get_projectsBRead-onlyIdempotent
List Studio Projects
Inputs: no named parameters.
get_project_snapshot_endpointCRead-onlyIdempotent
Get Project Snapshot
Inputs: project_id (required), project_snapshot_id (required).
get_project_snapshotsBRead-onlyIdempotent
List Studio Project Snapshots
Inputs: project_id (required).
get_pronunciation_dictionaries_metadataCRead-onlyIdempotent
Get Pronunciation Dictionaries
Inputs: sort, cursor, page_size, sort_direction, +1 more.
get_pronunciation_dictionary_metadataCRead-onlyIdempotent
Get Metadata For A Pronunciation Dictionary
Inputs: pronunciation_dictionary_id (required).
get_pronunciation_dictionary_version_plsBRead-onlyIdempotent
Get A Pls File With A Pronunciation Dictionary Version Rules
Inputs: version_id (required), dictionary_id (required).
get_public_llm_expected_cost_calculationC
Calculate Expected Llm Usage
Inputs: rag_enabled (required), prompt_length (required), number_of_pages (required).
get_pvc_sample_audioCRead-onlyIdempotent
Retrieve Voice Sample Audio
Inputs: voice_id (required), sample_id (required), remove_background_noise.
get_pvc_sample_speakersCRead-onlyIdempotent
Retrieve Speaker Separation Status
Inputs: voice_id (required), sample_id (required).
get_pvc_sample_visual_waveformCRead-onlyIdempotent
Retrieve Voice Sample Visual Waveform
Inputs: voice_id (required), sample_id (required).
get_pvc_voice_captchaCRead-onlyIdempotent
Get Pvc Voice Captcha
Inputs: voice_id (required).
get_rag_indexesCRead-onlyIdempotent
Get Rag Indexes Of The Specified Knowledgebase Document.
Inputs: documentation_id (required).
get_rag_index_overviewCRead-onlyIdempotent
Get Rag Index Overview.
Inputs: no named parameters.
get_resource_metadataCRead-onlyIdempotent
Get Resource
Inputs: resource_id (required), resource_type (required).
get_secret_dependencies_routeCRead-onlyIdempotent
Get Secret Dependencies By Type
Inputs: secret_id (required), resource_type (required), cursor, page_size.
get_secret_routeCRead-onlyIdempotent
Get Convai Workspace Secret
Inputs: secret_id (required).
get_secrets_routeCRead-onlyIdempotent
Get Convai Workspace Secrets
Inputs: cursor, search, page_size, dependency_limit.
get_service_account_api_keys_routeDRead-onlyIdempotent
Get Service Account Api Keys Route
Inputs: service_account_user_id (required).
get_settings_routeCRead-onlyIdempotent
Get Convai Settings
Inputs: no named parameters.
get_signed_url_deprecatedCRead-onlyIdempotent
Get Signed Url Deprecated upstream.
Inputs: agent_id (required), branch_id, version_id, environment, +2 more.
get_similar_library_voicesC
Get Similar Library Voices Spends ElevenLabs credits.
Inputs: top_k, audio_file_path, audio_file_base64, audio_file_filename, +1 more.
get_similar_voices_for_speakerBRead-onlyIdempotent
Search The Elevenlabs Library For Voices Similar To A Speaker. Deprecated upstream.
Inputs: dubbing_id (required), speaker_id (required).
get_single_use_tokenD
Create Single Use Token
Inputs: token_type (required).
get_speaker_audioCRead-onlyIdempotent
Retrieve Separated Speaker Audio
Inputs: voice_id (required), sample_id (required), speaker_id (required).
get_speech_engineCRead-onlyIdempotent
Get Speech Engine
Inputs: speech_engine_id (required).
get_speech_historyCRead-onlyIdempotent
List Generated Items
Inputs: search, source, model_id, voice_id, +5 more.
get_speech_history_item_by_idCRead-onlyIdempotent
Get History Item
Inputs: history_item_id (required).
get_test_invocation_routeCRead-onlyIdempotent
Get Test Invocation
Inputs: test_invocation_id (required).
get_text_to_speech_generationDRead-onlyIdempotent
Get Speech Generation
Inputs: generation_id (required).
get_tool_dependent_agents_routeCRead-onlyIdempotent
Get Dependent Agents List
Inputs: tool_id (required), cursor, page_size.
get_tool_executions_routeCRead-onlyIdempotent
Get Tool Executions
Inputs: tool_id (required), cursor, agent_id, end_time, +4 more.
get_tool_routeDRead-onlyIdempotent
Get Tool
Inputs: tool_id (required), environment.
get_tools_routeCRead-onlyIdempotent
Get Tools
Inputs: types, cursor, search, sort_by, +4 more.
get_transcript_by_idCRead-onlyIdempotent
Get Transcript By Id
Inputs: transcription_id (required).
get_user_infoCRead-onlyIdempotent
Get User Info
Inputs: no named parameters.
get_user_subscription_infoCRead-onlyIdempotent
Get User Subscription Info
Inputs: no named parameters.
get_user_voices_v2DRead-onlyIdempotent
Get Voices V2
Inputs: age, sort, accent, gender, +16 more.
get_version_metadata_routeCRead-onlyIdempotent
Get Agent Version Metadata
Inputs: agent_id (required), version_id (required).
get_video_generationDRead-onlyIdempotent
Get Video Generation
Inputs: generation_id (required).
get_voice_accentsDRead-onlyIdempotent
Get Voice Accents
Inputs: language, model_id.
get_voice_by_idCRead-onlyIdempotent
Get Voice
Inputs: voice_id (required), with_settings.
get_voicesCRead-onlyIdempotent
List Voices
Inputs: show_legacy.
get_voice_settingsCRead-onlyIdempotent
Get Voice Settings
Inputs: voice_id (required).
get_voice_settings_defaultBRead-onlyIdempotent
Get Default Voice Settings.
Inputs: no named parameters.
get_whatsapp_accountCRead-onlyIdempotent
Get Whatsapp Account
Inputs: phone_number_id (required).
get_workspace_audit_logsCRead-onlyIdempotent
Get Workspace Audit Logs
Inputs: limit, cursor, actor_uid, class_name, +3 more.
get_workspace_batch_callsCRead-onlyIdempotent
Get All Batch Calls For A Workspace.
Inputs: limit, agent_id, last_doc.
get_workspace_membersCRead-onlyIdempotent
Get Workspace Members
Inputs: no named parameters.
get_workspace_service_accountsCRead-onlyIdempotent
Get Workspace Service Accounts
Inputs: no named parameters.
get_workspace_webhooks_routeCRead-onlyIdempotent
List Workspace Webhooks
Inputs: include_usages.
handle_exotel_outbound_callD
Handle An Outbound Call Via Exotel
Inputs: agent_id (required), to_number (required), agent_phone_number_id (required), telephony_call_config, +1 more.
handle_sip_trunk_outbound_callC
Handle An Outbound Call Via Sip Trunk
Inputs: agent_id (required), to_number (required), agent_phone_number_id (required), telephony_call_config, +1 more.
handle_twilio_outbound_callD
Handle An Outbound Call Via Twilio
Inputs: agent_id (required), to_number (required), agent_phone_number_id (required), telephony_call_config, +2 more.
invite_userD
Invite User
Inputs: email (required), group_ids, seat_type, usage_limit, +1 more.
invite_users_bulkD
Invite Multiple Users
Inputs: emails (required), group_ids, seat_type, usage_limit.
list_agent_conversation_tickets_routeCRead-onlyIdempotent
List Agent Conversation Tickets
Inputs: agent_id (required), label, cursor, status, +6 more.
list_assetsCRead-onlyIdempotent
List Assets
Inputs: cursor, search, page_size.
list_auth_connectionsBRead-onlyIdempotent
Get Workspace Auth Connections
Inputs: no named parameters.
list_available_llmsCRead-onlyIdempotent
List Available Llms
Inputs: no named parameters.
list_chat_response_tests_routeCRead-onlyIdempotent
List Agent Response Tests
Inputs: types, cursor, search, page_size, +4 more.
list_conversation_tags_routeCRead-onlyIdempotent
List Conversation Tags
Inputs: cursor, page_size.
list_crawl_jobs_routeBRead-onlyIdempotent
List Ongoing And Recent Crawl Jobs Created By A User
Inputs: cursor, page_size, include_job_ids.
list_dubsCRead-onlyIdempotent
List Dubs
Inputs: cursor, order_by, page_size, dubbing_models, +6 more.
list_environment_variablesCRead-onlyIdempotent
List Environment Variables
Inputs: type, label, cursor, page_size, +1 more.
list_image_generationsCRead-onlyIdempotent
List Image Generations
Inputs: cursor, status, model_id, page_size.
list_mcp_servers_routeCRead-onlyIdempotent
List Mcp Servers
Inputs: no named parameters.
list_mcp_server_tools_routeCRead-onlyIdempotent
List Mcp Server Tools
Inputs: mcp_server_id (required), environment.
list_phone_numbers_routeCRead-onlyIdempotent
List Phone Numbers
Inputs: agent_id, provider, branch_id.
list_procedures_routeCRead-onlyIdempotent
List Procedures
Inputs: agent_id (required), branch_id (required), agent_version_id.
list_sip_messagesCRead-onlyIdempotent
Get Sip Messages For A Phone Number
Inputs: phone_number_id (required), cursor, page_size.
list_speech_enginesCRead-onlyIdempotent
List Speech Engines
Inputs: cursor, search, sort_by, page_size, +1 more.
list_test_invocations_routeCRead-onlyIdempotent
List Test Invocations
Inputs: cursor, search, agent_id, page_size.
list_text_to_speech_generationsCRead-onlyIdempotent
List Speech Generations
Inputs: cursor, status, model_id, page_size.
list_video_generationsCRead-onlyIdempotent
List Video Generations
Inputs: cursor, status, model_id, page_size.
list_whatsapp_accountsCRead-onlyIdempotent
List Whatsapp Accounts
Inputs: agent_id.
list_workspace_conversation_tickets_routeCRead-onlyIdempotent
List Workspace Conversation Tickets
Inputs: cursor, status, page_size, assignee_user_id.
merge_branch_into_targetC
Merge A Branch Into A Target Branch
Inputs: agent_id (required), source_branch_id (required), target_branch_id (required), force, +1 more.
merge_preview_routeCRead-onlyIdempotent
Preview Merged Configuration
Inputs: agent_id (required), source_branch_id (required), target_branch_id (required), force.
migrate_segmentsB
Move Segments Between Speakers Spends ElevenLabs credits. Deprecated upstream.
Inputs: dubbing_id (required), speaker_id (required), segment_ids (required).
patch_agent_settings_routeD
Patches An Agent Settings
Inputs: agent_id (required), name, tags, workflow, +6 more.
patch_pronunciation_dictionaryC
Update Pronunciation Dictionary
Inputs: pronunciation_dictionary_id (required), name, archived.
post_agent_avatar_routeD
Post Agent Avatar
Inputs: agent_id (required), avatar_file_path, avatar_file_base64, avatar_file_filename.
post_agent_hold_audio_routeD
Post Agent Hold Audio
Inputs: agent_id (required), hold_audio_file_path, hold_audio_file_base64, hold_audio_file_filename.
post_conversation_feedback_routeD
Send Conversation Feedback
Inputs: conversation_id (required), feedback.
post_knowledge_base_bulk_delete_routeC
Bulk Delete Knowledge Base Documents
Inputs: document_ids (required), force.
post_knowledge_base_bulk_move_routeC
Bulk Move Entities To Folder
Inputs: document_ids (required), move_to.
post_knowledge_base_move_routeC
Move Entity To Folder
Inputs: document_id (required), move_to.
public_create_orderC
Create Order Spends ElevenLabs credits.
Inputs: sandbox.
public_get_available_languagesCRead-onlyIdempotent
Get Available Languages
Inputs: order_item_kind (required).
public_get_media_infoCRead-onlyIdempotent
Get Media Info
Inputs: media_id (required), order_id (required).
public_get_orderCRead-onlyIdempotent
Get Order
Inputs: order_id (required).
public_get_order_deliverablesCRead-onlyIdempotent
Get Order Deliverables
Inputs: order_id (required).
public_list_ordersCRead-onlyIdempotent
List Orders
Inputs: offset, status, end_date, page_size, +1 more.
public_register_mediaC
Register Media Spends ElevenLabs credits.
Inputs: order_id (required), declared_language (required), media_url, media_path, +4 more.
public_remove_order_itemCDestructiveIdempotent
Remove Order Item
Inputs: item_id (required), order_id (required).
public_submit_orderB
Submit Order Spends ElevenLabs credits.
Inputs: order_id (required).
public_update_orderC
Update Order Spends ElevenLabs credits.
Inputs: request (required), order_id (required).
public_upsert_order_itemC
Upsert Order Item Spends ElevenLabs credits.
Inputs: request (required), order_id (required).
query_agent_knowledge_base_rag_routeC
Query Agent Knowledge Base Rag
Inputs: query (required), agent_id (required), branch_id, use_agent_defaults, +2 more.
rag_index_statusD
Compute Rag Index.
Inputs: model (required), documentation_id (required).
rebase_branch_onto_mainC
Rebase A Branch Onto Main
Inputs: agent_id (required), branch_id (required).
rebase_preview_routeCRead-onlyIdempotent
Preview Rebased Configuration
Inputs: agent_id (required), branch_id (required).
redirect_to_mintlifyDRead-onlyIdempotent
Redirect To Mintlify
Inputs: no named parameters.
refresh_url_document_routeC
Refresh Url Document Content
Inputs: documentation_id (required).
register_twilio_callC
Register A Twilio Call And Return Twiml
Inputs: agent_id (required), to_number (required), from_number (required), direction, +1 more.
remove_mcp_server_tool_approval_routeCDestructiveIdempotent
Delete Mcp Server Tool Approval
Inputs: tool_name (required), mcp_server_id (required).
remove_mcp_tool_config_override_routeCDestructiveIdempotent
Delete Mcp Tool Configuration Override
Inputs: tool_name (required), mcp_server_id (required).
remove_memberC
Delete Member From User Group
Inputs: email (required), group_id (required).
remove_procedure_routeCDestructiveIdempotent
Remove Procedure
Inputs: agent_id (required), branch_id (required), procedure_id (required).
remove_rulesC
Remove Rules From The Pronunciation Dictionary
Inputs: rule_strings (required), pronunciation_dictionary_id (required).
renderA
Render Audio Or Video For The Given Language Spends ElevenLabs credits. Deprecated upstream.
Inputs: language (required), dubbing_id (required), render_type (required), normalize_volume.
replicate_voice_to_isolated_environmentC
Replicate Voice To Isolated Environment
Inputs: voice_id (required), target_workspace_id (required), preserve_voice_id.
request_pvc_manual_verificationC
Request Manual Verification
Inputs: voice_id (required), extra_text, files_paths, files_filenames, +1 more.
requests_listD
List Api Requests
Inputs: sort, limit, search, filters, +2 more.
resolve_conversation_reference_routeDRead-onlyIdempotent
Resolve Conversation Reference
Inputs: agent_id (required), reference (required).
resubmit_tests_routeD
Resubmit Tests
Inputs: agent_id (required), test_run_ids (required), test_invocation_id (required), branch_id, +1 more.
retry_batch_callC
Retry A Batch Call.
Inputs: batch_id (required).
run_agent_test_suite_routeC
Run Tests On The Agent
Inputs: tests (required), agent_id (required), branch_id, repeat_count, +1 more.
run_conversation_analysisC
Run Conversation Analysis
Inputs: conversation_id (required).
run_conversation_evaluationsC
Run Conversation Evaluation
Inputs: evaluation_id (required), conversation_id (required), scope.
run_conversation_simulation_routeC
Simulates A Conversation Deprecated upstream.
Inputs: agent_id (required), simulation_specification (required), new_turns_limit, extra_evaluation_criteria.
run_conversation_simulation_route_streamC
Simulates A Conversation (Stream) Deprecated upstream.
Inputs: agent_id (required), simulation_specification (required), new_turns_limit, extra_evaluation_criteria.
run_pvc_voice_trainingD
Run Pvc Training
Inputs: voice_id (required), model_id.
search_groupsCRead-onlyIdempotent
Search User Groups
Inputs: name (required).
search_knowledge_base_content_routeCRead-onlyIdempotent
Search Knowledge Base Content
Inputs: query (required), types, cursor, page_size.
separate_song_stemsC
Stem Separation Spends ElevenLabs credits. Returns application/zip bytes; pass output_path to save them.
Inputs: file_path, file_base64, output_path, file_filename, +3 more.
set_rulesC
Set Rules On The Pronunciation Dictionary
Inputs: rules (required), pronunciation_dictionary_id (required).
set_third_party_disabling_policyD
Set Workspace Third-Party Disabling Policy
Inputs: third_party_disable_allowed.
smart_search_conversation_messages_routeCRead-onlyIdempotent
Smart Search Conversation Messages
Inputs: text_query (required), cursor, agent_id, page_size.
sound_generationC
Sound Generation Spends ElevenLabs credits. Returns audio/mpeg bytes; pass output_path to save them.
Inputs: text (required), loop, model_id, output_path, +3 more.
speech_to_speech_fullB
Speech To Speech Spends ElevenLabs credits. Returns audio/mpeg bytes; pass output_path to save them.
Inputs: voice_id (required), seed, model_id, audio_path, +9 more.
speech_to_speech_streamB
Speech To Speech Streaming Spends ElevenLabs credits. Returns audio/mpeg bytes; pass output_path to save them.
Inputs: voice_id (required), seed, model_id, audio_path, +9 more.
speech_to_textC
Speech To Text Spends ElevenLabs credits.
Inputs: model_id (required), seed, token, diarize, +26 more.
start_speaker_separationC
Start Speaker Separation
Inputs: voice_id (required), sample_id (required).
stream_chapter_snapshot_audioA
Stream Chapter Audio Spends ElevenLabs credits. Returns audio/mpeg bytes; pass output_path to save them.
Inputs: chapter_id (required), project_id (required), chapter_snapshot_id (required), output_path, +1 more.
stream_composeB
Stream Composed Music Spends ElevenLabs credits. Returns audio/* bytes; pass output_path to save them.
Inputs: seed, prompt, model_id, finetune_id, +11 more.
stream_project_snapshot_archive_endpointA
Stream Archive With Studio Project Audio Spends ElevenLabs credits. Returns application/x-zip bytes; pass output_path to save them.
Inputs: project_id (required), project_snapshot_id (required), output_path.
stream_project_snapshot_audio_endpointC
Stream Studio Project Audio Spends ElevenLabs credits.
Inputs: project_id (required), project_snapshot_id (required), convert_to_mpeg.
text_search_conversation_messages_routeDRead-onlyIdempotent
Text Search Conversation Messages
Inputs: text_query (required), cursor, sort_by, user_id, +30 more.
text_to_dialogueB
Text To Dialogue (Multi-Voice) Spends ElevenLabs credits. Returns audio/mpeg bytes; pass output_path to save them.
Inputs: inputs (required), seed, model_id, settings, +6 more.
text_to_dialogue_full_with_timestampsC
Text To Dialogue With Timestamps Spends ElevenLabs credits.
Inputs: inputs (required), seed, model_id, settings, +5 more.
text_to_dialogue_streamB
Text To Dialogue (Multi-Voice) Streaming Spends ElevenLabs credits. Returns audio/mpeg bytes; pass output_path to save them.
Inputs: inputs (required), seed, model_id, settings, +6 more.
text_to_dialogue_stream_with_timestampsD
Text To Dialogue Streaming With Timestamps Spends ElevenLabs credits.
Inputs: inputs (required), seed, model_id, settings, +5 more.
text_to_speech_fullB
Text To Speech Spends ElevenLabs credits. Returns audio/mpeg bytes; pass output_path to save them.
Inputs: text (required), voice_id (required), seed, model_id, +14 more.
text_to_speech_full_with_timestampsD
Text To Speech With Timestamps Spends ElevenLabs credits.
Inputs: text (required), voice_id (required), seed, model_id, +13 more.
text_to_speech_streamB
Text To Speech Streaming Spends ElevenLabs credits. Returns audio/mpeg bytes; pass output_path to save them.
Inputs: text (required), voice_id (required), seed, model_id, +14 more.
text_to_speech_stream_with_timestampsC
Text To Speech Streaming With Timestamps Spends ElevenLabs credits.
Inputs: text (required), voice_id (required), seed, model_id, +13 more.
text_to_voiceC
[Deprecated] Generate A Voice Preview From Description Spends ElevenLabs credits. Deprecated upstream.
Inputs: voice_description (required), seed, text, quality, +5 more.
text_to_voice_designC
Design A Voice. Spends ElevenLabs credits.
Inputs: voice_description (required), seed, text, quality, +11 more.
text_to_voice_preview_streamCRead-onlyIdempotent
Text To Voice Preview Streaming Returns audio/mpeg bytes; pass output_path to save them.
Inputs: generated_voice_id (required), output_path.
text_to_voice_remixC
Remix A Voice. Spends ElevenLabs credits.
Inputs: voice_id (required), voice_description (required), seed, text, +8 more.
transcribeC
Transcribes Segments Spends ElevenLabs credits. Deprecated upstream.
Inputs: segments (required), dubbing_id (required).
translateB
Translates All Or Some Segments And Languages Spends ElevenLabs credits. Deprecated upstream.
Inputs: segments (required), languages (required), dubbing_id (required).
unassign_conversation_tag_routeDDestructiveIdempotent
Unassign Conversation Tag
Inputs: tag_id (required), conversation_id (required).
update_agent_conversation_ticket_routeD
Update Agent Conversation Ticket
Inputs: agentqa_ticket_id (required), status, assignee_user_id.
update_agent_response_test_routeDIdempotent
Update Agent Response Test
Inputs: test_id (required), name, type, environment, +18 more.
update_agent_test_folder_routeC
Update Agent Test Folder
Inputs: name (required), folder_id (required).
update_auth_connectionD
Update Workspace Auth Connection
Inputs: auth_connection_id (required), token, issuer, key_id, +16 more.
update_branch_routeD
Update Agent Branch
Inputs: agent_id (required), branch_id (required), name, is_archived, +1 more.
update_conversation_tag_routeD
Update Conversation Tag
Inputs: tag_id (required), title, description.
update_dashboard_settings_routeC
Update Convai Dashboard Settings
Inputs: charts.
update_document_routeC
Update Document
Inputs: documentation_id (required), name, content.
update_environment_variableD
Update Environment Variable
Inputs: values (required), env_var_id (required).
update_file_document_routeC
Update File Document
Inputs: documentation_id (required), file_path, file_base64, file_filename.
update_finetuneC
Update Music Finetune Spends ElevenLabs credits.
Inputs: finetune_id (required), name, tags, visibility, +1 more.
update_mcp_server_approval_policy_routeC
Update Mcp Server Approval Policy Deprecated upstream.
Inputs: mcp_server_id (required), approval_policy (required).
update_mcp_server_config_routeC
Update Mcp Server Configuration
Inputs: mcp_server_id (required), request_meta, secret_token, execution_mode, +11 more.
update_mcp_tool_config_override_routeD
Update Mcp Tool Configuration Override
Inputs: tool_name (required), mcp_server_id (required), assignments, environment, +10 more.
update_phone_number_routeD
Update Phone Number
Inputs: phone_number_id (required), label, agent_id, branch_id, +5 more.
update_procedure_draft_routeC
Update Procedure Draft
Inputs: name (required), type (required), content (required), agent_id (required), +3 more.
update_pronunciation_dictionariesD
Create Pronunciation Dictionaries Spends ElevenLabs credits.
Inputs: project_id (required), pronunciation_dictionary_locators (required), invalidate_affected_text.
update_secret_routeC
Update Convai Workspace Secret
Inputs: name (required), type (required), value (required), secret_id (required).
update_segment_languageC
Modify A Single Segment Spends ElevenLabs credits. Deprecated upstream.
Inputs: language (required), dubbing_id (required), segment_id (required), text, +2 more.
update_settings_routeD
Update Convai Settings
Inputs: webhooks, can_use_mcp_servers, default_livekit_stack, rag_retention_period_days, +2 more.
update_speakerC
Update Metadata For A Speaker Spends ElevenLabs credits. Deprecated upstream.
Inputs: dubbing_id (required), speaker_id (required), voice_id, languages, +4 more.
update_speech_engineD
Update Speech Engine
Inputs: speech_engine_id (required), asr, tts, vad, +9 more.
update_tool_routeD
Update Tool
Inputs: tool_id (required), tool_config (required), response_mocks.
update_whatsapp_accountD
Update Whatsapp Account
Inputs: phone_number_id (required), enable_messaging, assigned_agent_id, enable_typing_indicator, +1 more.
update_workspace_memberD
Update Member
Inputs: email (required), is_locked, workspace_role, workspace_seat_type.
upload_assetD
Upload Asset
Inputs: name (required), asset_path, asset_base64, asset_filename.
upload_file_routeD
Upload File
Inputs: conversation_id (required), file_path, file_base64, file_filename.
upload_songC
Upload Music Spends ElevenLabs credits.
Inputs: file_path, file_base64, file_filename, with_timestamps, +2 more.
usage_by_product_over_timeD
Get Workspace Usage
Inputs: end_time (required), start_time (required), filters, group_by, +2 more.
usage_charactersCRead-onlyIdempotent
Get Characters Usage Metrics (Deprecated) Deprecated upstream.
Inputs: end_unix (required), start_unix (required), metric, breakdown_type, +3 more.
verify_pvc_voice_captchaC
Verify Pvc Voice Captcha
Inputs: voice_id (required), recording_path, recording_base64, recording_filename.
video_to_musicC
Video To Music Spends ElevenLabs credits. Returns application/zip bytes; pass output_path to save them.
Inputs: tags, model_id, description, output_path, +5 more.
whatsapp_outbound_callC
Make An Outbound Call Via Whatsapp
Inputs: agent_id (required), whatsapp_user_id (required), whatsapp_phone_number_id (required), whatsapp_call_permission_request_template_name (required), +2 more.
whatsapp_outbound_messageC
Send An Outbound Message Via Whatsapp
Inputs: agent_id (required), template_name (required), template_params (required), whatsapp_user_id (required), +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
C2/5.0
Scored across 390 tools
Disambiguation2/5
Many tools overlap heavily: text_to_speech_full/stream/with_timestamps variants, multiple delete/get tools for the same resource, and deprecated duplicates. Descriptions are present but the boundaries between similar tools are unclear, causing frequent misselection risk.
Naming Consistency2/5
Naming uses mixed patterns: verb_noun (get_agent_route), noun_verb (dubbing_language_create), inconsistent suffixes (_route, _endpoint), random prefixes (public_, deprecated markers), and several one-word tools (disable, dub, render). No predictable convention.
Tool Count1/5
390 tools is an extreme mismatch for a single API surface. The massive duplication and inclusion of deprecated endpoints indicate poor curation rather than a well-scoped set.
Completeness4/5
The tool set covers a wide range of ElevenLabs capabilities: TTS, STS, dubbing, agents, music, voices, workspace, billing, and more. Minor gaps exist (e.g., some deprecated tools lack modern replacements), but core workflows are largely present.
Related MCP Connectors
Manage ElevenLabs voice agents and generate speech, music, sound effects, images, and video.
ElevenLabs in natural language: generate speech in any language, create and manage voices, compose m
Audio and video tools for your AI assistant: remove noise, enhance voices, transcribe, and more.
214 tools for AI agents over one MCP endpoint: image, video, audio, 3D, data, storage, mail, GPUs.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides comprehensive access to ElevenLabs AI audio features including text-to-speech, voice cloning, sound generation, and audio isolation. Enables users to generate high-quality speech, manage voices, transform audio, and access ElevenLabs services through natural language interactions.103 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables seamless integration with ElevenLabs Conversational AI to manage agents, tools, and knowledge base sources. It supports RAG indexing, webhook integration, and document management for building advanced voice-enabled AI agents.MIT
- AlicenseAqualityFmaintenanceEnables text-to-speech conversion using ElevenLabs API with voice management, streaming support, and multiple models.51MIT