Skip to main content
Glama
AIWerk

@aiwerk/mcp-server-elevenlabs

by AIWerk
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

text_to_speech_stream

Convert text into speech audio using ElevenLabs, returning MP3 bytes or saving to a file. Specify voice_id and text to generate speech.

Instructions

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

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
seedNo
textYesThe text that will get converted into speech.
model_idNoIdentifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property.
voice_idYesVoice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.
next_textNo
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).
language_codeNo
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
previous_textNo
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.
use_pvc_as_ivcNoIf true, we won't use PVC version of the voice for the generation but the IVC version. This is a temporary workaround for higher latency in PVC versions.
voice_settingsNo
next_request_idsNo
previous_request_idsNo
apply_text_normalizationNoThis parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped.
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
apply_language_text_normalizationNoThis parameter controls language text normalization. This helps with proper pronunciation of text in some supported languages. WARNING: This parameter can heavily increase the latency of the request. Currently only supported for Japanese.
pronunciation_dictionary_locatorsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3/5.0
Behavior4/5

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

Given readOnlyHint=false and no output schema, the description usefully discloses two behavioral facts the annotations don't: it consumes ElevenLabs credits (a cost/side-effect) and it returns audio/mpeg bytes that can be persisted via output_path. It does not explain streaming semantics (chunking, latency, partial delivery), which is the one notable gap.

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 tight sentences, front-loaded with the cost warning and then the return-handling instruction. Slightly wasteful in that the opening phrase just echoes the tool title, but nothing is padded.

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?

For an 18-parameter generation tool with no output schema, the description covers cost and return handling but leaves streaming behavior and most parameters unexplained. It is adequate for a basic call but incomplete given the tool's complexity.

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

Parameters2/5

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

With 18 parameters at only 56% schema coverage, roughly half the parameters (seed, next_text, language_code, previous_text, next/previous_request_ids, pronunciation_dictionary_locators) are undocumented in both schema and description. The description only touches output_path, which the schema already explains in more detail, so it does not compensate for the coverage gap.

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

Purpose3/5

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

The description largely restates the tool name ("Text To Speech Streaming") and only adds the credit-spend fact. It does not differentiate from close siblings like text_to_speech_full or text_to_speech_stream_with_timestamps, so an agent cannot tell from the text alone why it would pick this over the full or timestamped variants.

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 guidance on when to use this versus text_to_speech_full, text_to_speech_stream_with_timestamps, or text_to_dialogue_stream. The only routing-ish hint is that output_path can be passed, which is a parameter detail rather than a usage rule.

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