Skip to main content
Glama
AIWerk

@aiwerk/mcp-server-elevenlabs

by AIWerk
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

speech_to_speech_stream

Transforms input audio into synthesized speech using a chosen voice and streams audio/mpeg bytes; set output_path to save the generated audio.

Instructions

Speech To Speech Streaming Spends ElevenLabs credits. Returns audio/mpeg bytes; pass output_path to save them.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
seedNoIf specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295.
model_idNoIdentifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for speech to speech, you can check this using the can_do_voice_conversion property.
voice_idYesVoice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.
audio_pathNoThe audio file which holds the content and emotion that will control the generated speech. Local path. Required for this call.
file_formatNoThe format of input audio. Options are 'pcm_s16le_16' or 'other' For `pcm_s16le_16`, the input audio must be 16-bit PCM at a 16kHz sample rate, single channel (mono), and little-endian byte order. Latency will be lower than with passing an encoded waveform.
output_pathNoWhere to write the returned bytes. Relative paths resolve against ELEVENLABS_OUTPUT_DIR. Omit it to get the data inline as base64 (small files only).
audio_base64NoBase64 contents for "audio". Use this when the server cannot read your local disk.
output_formatNoOutput format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pr
audio_filenameNoFilename to send for "audio". Some endpoints infer the audio format from it.
enable_loggingNoWhen enable_logging is set to false zero retention mode will be used for the request. This will mean history features are unavailable for this request, including request stitching. Zero retention mode may only be used by enterprise customers.
voice_settingsNoVoice settings overriding stored settings for the given voice. They are applied only on the given request. Needs to be send as a JSON encoded string.
remove_background_noiseNoIf set, will remove the background noise from your audio input using our audio isolation model. Only applies to Voice Changer.
optimize_streaming_latencyNoYou can turn on latency optimizations at some cost of quality. The best possible final latency varies by model. Possible values: 0 - default mode (no latency optimizations) 1 - normal latency optimizations (about 50% of possible latency improvement of option 3) 2 - strong latency optimizations (abou

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds non-obvious behavioral context: it spends ElevenLabs credits, returns audio/mpeg bytes, and the output_path parameter controls whether bytes are saved or returned inline. Annotations cover safety (readOnlyHint=false, destructiveHint=false, etc.) but this credit-spending and output-format detail goes beyond what annotations declare.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the cost warning and return format. No wasted words, though it could be slightly more structured (e.g., separating cost from output behavior).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 13 parameters, no output schema, and rich sibling context, the description is minimal. It covers cost and output handling but omits required input parameters (voice_id is required, audio_path is 'Required for this call') and doesn't mention that this is a streaming endpoint. More would be expected for a tool with this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 13 parameters thoroughly. The description only adds meaning for output_path (saving bytes) and implies the return type, but doesn't explain other important params like voice_id, audio_path, or audio_base64. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the resource (speech-to-speech streaming) and a key behavior (returns audio/mpeg bytes). However, it doesn't explicitly differentiate this streaming variant from the sibling 'speech_to_speech_full' or clarify that it performs voice conversion rather than text-to-speech.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like speech_to_speech_full or text_to_speech_stream. The only conditional hint is 'pass output_path to save them', which is about output handling, not tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools