$ ~/registry/skill/composiohq-composio-skills-elevenlabs-automation

SKILL

ElevenLabs Automation

Name: ElevenLabs Automation
Author: Composio

Automate ElevenLabs text-to-speech, voice management, and audio history workflows.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 64.7k

Summary

The material itself appears to be an open-source prompt/workflow document with strong community trust, so overall risk is relatively low. However, actual use routes through a remote Composio MCP service and requires connecting an ElevenLabs account/API credential, so network egress and third-party credential delegation still deserve attention.

CredentialsCaution

There is a mismatch between the metadata and README: the header says “no keys,” but the README explicitly instructs users to connect an ElevenLabs account via “API key authentication.” This means the real workflow involves ElevenLabs credentials and likely delegated calls through Composio MCP; this is a normal third-party auth pattern, but key storage, scope, and revocation should be verified.

Network egressCaution

The README explicitly requires adding the remote MCP endpoint `https://rube.app/mcp` and supports ElevenLabs operations such as text-to-speech, voice browsing, and history retrieval, indicating that user text, voice metadata, and generated outputs will be sent through third-party services. The endpoint appears functionally relevant, but it conflicts with the metadata claim of “no remote host,” so actual data flows and retention practices should be verified.

Code executionLow risk

Based on the provided checks, this is prompt-only material, and there is no instruction to run scripts locally, install binaries, spawn local processes, or request system-level execution privileges. From the available material, no additional code-execution surface is exposed.

Data accessCaution

Its stated capabilities include submitting text for speech generation, browsing voices, checking subscription credits, streaming audio, and retrieving historical audio items, so it can access resources and history within the connected ElevenLabs account. No local filesystem access or obviously excessive permissions are described, but historical content and generated audio may still contain sensitive business text.

Supply chainLow risk

Positive signals are strong: the source is a GitHub open-source repository with high community adoption (about 64.7k stars), and the visible content is mainly auditable skill documentation. Caveats remain—license is unspecified, maintenance status is unknown, and real operation depends on external Composio MCP/services—so repository freshness and the reputation of the external service should still be checked.

Recommendations

Before enabling it, verify the actual data flow between Composio MCP and ElevenLabs, including logging retention and whether prompt text/audio history is stored.
Use least-privilege, separately revocable ElevenLabs API credentials and rotate them regularly instead of reusing a long-lived primary account key.
Do not submit highly sensitive text to this workflow; if necessary, redact or segment the content first.
Check the repository’s recent maintenance status, license details, and the official relationship of Composio/`rube.app` before production use.

Audited by: gpt-5.4 · 2026-06-16

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "ElevenLabs Automation" skill from askskill:
1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/elevenlabs-automation/SKILL.md
2. Save it as ~/.claude/skills/elevenlabs-automation/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

ElevenLabs Automation

Automate your ElevenLabs text-to-speech workflows -- convert text to natural speech, browse the voice library, inspect voice details, check subscription credits, select TTS models, stream audio for low-latency delivery, and retrieve previously generated audio from history.

Toolkit docs: composio.dev/toolkits/elevenlabs

Setup

Add the Composio MCP server to your client: https://rube.app/mcp
Connect your ElevenLabs account when prompted (API key authentication)
Start using the workflows below

Core Workflows

1. Generate Speech from Text

Use ELEVENLABS_TEXT_TO_SPEECH to convert text into a downloadable audio file.

Tool: ELEVENLABS_TEXT_TO_SPEECH
Inputs:
  - voice_id: string (required) -- obtain from ELEVENLABS_GET_VOICES
  - text: string (required) -- max ~10,000 chars (most models), 30,000 (Flash/Turbo v2), 40,000 (v2.5)
  - model_id: string (default "eleven_monolingual_v1") -- e.g., "eleven_multilingual_v2"
  - output_format: string (default "mp3_44100_128") -- see formats below
  - optimize_streaming_latency: integer (0-4; NOT supported with eleven_v3)
  - seed: integer (optional, for reproducibility -- not guaranteed)
  - pronunciation_dictionary_locators: array (optional, up to 3 dictionaries)

Output formats:

MP3: mp3_22050_32, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192 (Creator+)
PCM: pcm_16000, pcm_22050, pcm_24000, pcm_44100 (Pro+)
uLaw: ulaw_8000 (for Twilio)

Important: Output is a file object with a presigned download link at data.file.s3url (expires in ~1 hour). Download promptly.

2. Browse Available Voices

Use ELEVENLABS_GET_VOICES to list all voices with their attributes and settings.

Tool: ELEVENLABS_GET_VOICES
Inputs: (none)

Returns an array at data.voices[] with voice_id, name, labels (gender, accent, use_case), and settings.

3. Inspect a Specific Voice

Use ELEVENLABS_GET_VOICE to get detailed metadata for a candidate voice before synthesis.

Tool: ELEVENLABS_GET_VOICE
Inputs:
  - voice_id: string (required) -- e.g., "21m00Tcm4TlvDq8ikWAM"
  - with_settings: boolean (default false) -- include detailed voice settings

4. Check Subscription and Credits

Use ELEVENLABS_GET_USER_SUBSCRIPTION_INFO to verify plan limits and remaining credits before bulk generation.

Tool: ELEVENLABS_GET_USER_SUBSCRIPTION_INFO
Inputs: (none)

5. List Available TTS Models

Use ELEVENLABS_GET_MODELS to discover compatible models and filter by can_do_text_to_speech: true.

Tool: ELEVENLABS_GET_MODELS
Inputs: (none)

6. Stream Audio and Retrieve History

Use ELEVENLABS_TEXT_TO_SPEECH_STREAM for low-latency streamed delivery, and ELEVENLABS_GET_AUDIO_FROM_HISTORY_ITEM to re-download previously generated audio.

Tool: ELEVENLABS_TEXT_TO_SPEECH_STREAM
  - Same core inputs as TEXT_TO_SPEECH but returns a stream for low-latency playback

Tool: ELEVENLABS_GET_AUDIO_FROM_HISTORY_ITEM
  - history_item_id: string (required) -- ID from a previous generation

Known Pitfalls

Pitfall	Detail
Text length limits	Most models cap at ~10,000-20,000 chars per request. Oversized input returns HTTP 400. Split long text into chunks (~5000 chars) and generate per chunk.
Output is a presigned URL	`ELEVENLABS_TEXT_TO_SPEECH` returns `data.file.s3url` with a ~1 hour expiry (X-Amz-Expires=3600). Download the audio file promptly.
Quota and credit errors	HTTP 401 with `quota_exceeded` or HTTP 402 `payment_required` means insufficient credits or tier restrictions. Check with `ELEVENLABS_GET_USER_SUBSCRIPTION_INFO` before bulk jobs.
Voice permissions	HTTP 401 with `missing_permissions` means the API key lacks `voices_read` scope. Verify key permissions.