elevenlabs-apiElevenLabs API integration with managed authentication. AI-powered text-to-speech, voice cloning, sound effects, and audio processing. Use this skill when users want to generate speech from text, clone voices, create sound effects, or process audio. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).
Install via ClawdBot CLI:
clawdbot install byungkyu/elevenlabs-apiAccess the ElevenLabs API with managed authentication. Generate lifelike speech from text, clone voices, create sound effects, and process audio.
# List available voices
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://gateway.maton.ai/elevenlabs/v1/voices')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOFhttps://gateway.maton.ai/elevenlabs/{native-api-path}Replace {native-api-path} with the actual ElevenLabs API endpoint path. The gateway proxies requests to api.elevenlabs.io and automatically injects your API key.
All requests require the Maton API key in the Authorization header:
Authorization: Bearer $MATON_API_KEYEnvironment Variable: Set your API key as MATON_API_KEY:
export MATON_API_KEY="YOUR_API_KEY"Manage your ElevenLabs connections at https://ctrl.maton.ai.
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections?app=elevenlabs&status=ACTIVE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOFpython <<'EOF'
import urllib.request, os, json
data = json.dumps({'app': 'elevenlabs'}).encode()
req = urllib.request.Request('https://ctrl.maton.ai/connections', data=data, method='POST')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Content-Type', 'application/json')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOFpython <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOFResponse:
{
"connection": {
"connection_id": "ff2079b1-f40a-43b7-a807-1d5deea29c5b",
"status": "ACTIVE",
"creation_time": "2026-02-12T00:50:40.292363Z",
"last_updated_time": "2026-02-12T00:51:14.547893Z",
"url": "https://connect.maton.ai/?session_token=...",
"app": "elevenlabs",
"metadata": {}
}
}Open the returned url in a browser to complete authorization.
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}', method='DELETE')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOFIf you have multiple ElevenLabs connections, specify which one to use with the Maton-Connection header:
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://gateway.maton.ai/elevenlabs/v1/voices')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
req.add_header('Maton-Connection', 'ff2079b1-f40a-43b7-a807-1d5deea29c5b')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOFIf omitted, the gateway uses the default (oldest) active connection.
POST /elevenlabs/v1/text-to-speech/{voice_id}
Content-Type: application/json
{
"text": "Hello, this is a test of the ElevenLabs API.",
"model_id": "eleven_multilingual_v2",
"voice_settings": {
"stability": 0.5,
"similarity_boost": 0.75
}
}Returns audio data (mp3 by default).
Query parameters:
output_format - Audio format (e.g., mp3_44100_128, pcm_16000, pcm_22050)POST /elevenlabs/v1/text-to-speech/{voice_id}/stream
Content-Type: application/json
{
"text": "Hello, this is streamed audio.",
"model_id": "eleven_multilingual_v2"
}Returns streaming audio data.
POST /elevenlabs/v1/text-to-speech/{voice_id}/with-timestamps
Content-Type: application/json
{
"text": "Hello world",
"model_id": "eleven_multilingual_v2"
}Returns audio with word-level timestamps.
GET /elevenlabs/v1/voicesReturns all available voices including premade and cloned voices.
GET /elevenlabs/v1/voices/{voice_id}Returns metadata about a specific voice.
GET /elevenlabs/v1/voices/settings/defaultGET /elevenlabs/v1/voices/{voice_id}/settingsPOST /elevenlabs/v1/voices/add
Content-Type: multipart/form-data
name: My Cloned Voice
files: [audio_sample.mp3]
description: A custom voice clone
remove_background_noise: falsePATCH /elevenlabs/v1/voices/{voice_id}/edit
Content-Type: multipart/form-data
name: Updated Voice Name
description: Updated descriptionDELETE /elevenlabs/v1/voices/{voice_id}GET /elevenlabs/v1/modelsReturns available models:
eleven_multilingual_v2 - Latest multilingual modeleleven_turbo_v2_5 - Low-latency modeleleven_monolingual_v1 - Legacy English model (deprecated)GET /elevenlabs/v1/userGET /elevenlabs/v1/user/subscriptionReturns subscription details including character limits and usage.
GET /elevenlabs/v1/history?page_size=100Query parameters:
page_size - Number of items per page (default: 100, max: 1000)start_after_history_item_id - Cursor for paginationvoice_id - Filter by voiceGET /elevenlabs/v1/history/{history_item_id}GET /elevenlabs/v1/history/{history_item_id}/audioReturns the audio file for a history item.
DELETE /elevenlabs/v1/history/{history_item_id}POST /elevenlabs/v1/history/download
Content-Type: application/json
{
"history_item_ids": ["id1", "id2", "id3"]
}Returns a zip file with the requested audio files.
POST /elevenlabs/v1/sound-generation
Content-Type: application/json
{
"text": "A thunderstorm with heavy rain and distant thunder",
"duration_seconds": 10.0
}Query parameters:
output_format - Audio format (e.g., mp3_44100_128)POST /elevenlabs/v1/audio-isolation
Content-Type: multipart/form-data
audio: [audio_file.mp3]Returns cleaned audio with background noise removed.
POST /elevenlabs/v1/audio-isolation/stream
Content-Type: multipart/form-data
audio: [audio_file.mp3]POST /elevenlabs/v1/speech-to-text
Content-Type: multipart/form-data
audio: [audio_file.mp3]
model_id: scribe_v1Returns transcription with optional word-level timestamps.
POST /elevenlabs/v1/speech-to-speech/{voice_id}
Content-Type: multipart/form-data
audio: [source_audio.mp3]
model_id: eleven_multilingual_sts_v2Transforms audio to use a different voice while preserving intonation.
GET /elevenlabs/v1/projectsGET /elevenlabs/v1/projects/{project_id}POST /elevenlabs/v1/projects
Content-Type: application/json
{
"name": "My Audiobook Project",
"default_title_voice_id": "voice_id",
"default_paragraph_voice_id": "voice_id"
}GET /elevenlabs/v1/pronunciation-dictionariesPOST /elevenlabs/v1/pronunciation-dictionaries/add-from-file
Content-Type: multipart/form-data
name: My Dictionary
file: [lexicon.pls]ElevenLabs API responses include useful headers:
x-character-count - Characters used in the requestrequest-id - Unique request identifierHistory and other list endpoints use cursor-based pagination:
GET /elevenlabs/v1/history?page_size=100&start_after_history_item_id=last_item_idconst response = await fetch(
'https://gateway.maton.ai/elevenlabs/v1/text-to-speech/JBFqnCBsd6RMkjVDRZzb',
{
method: 'POST',
headers: {
'Authorization': `Bearer ${process.env.MATON_API_KEY}`,
'Content-Type': 'application/json'
},
body: JSON.stringify({
text: 'Hello world!',
model_id: 'eleven_multilingual_v2'
})
}
);
const audioBuffer = await response.arrayBuffer();import os
import requests
response = requests.post(
'https://gateway.maton.ai/elevenlabs/v1/text-to-speech/JBFqnCBsd6RMkjVDRZzb',
headers={'Authorization': f'Bearer {os.environ["MATON_API_KEY"]}'},
json={
'text': 'Hello world!',
'model_id': 'eleven_multilingual_v2'
}
)
audio_data = response.content
with open('output.mp3', 'wb') as f:
f.write(audio_data)import os
import requests
response = requests.get(
'https://gateway.maton.ai/elevenlabs/v1/voices',
headers={'Authorization': f'Bearer {os.environ["MATON_API_KEY"]}'}
)
voices = response.json()
for voice in voices['voices']:
print(f"{voice['name']}: {voice['voice_id']}")codec_sample_rate_bitrate (e.g., mp3_44100_128)eleven_multilingual_v2 (recommended), eleven_turbo_v2_5 (low latency)curl -g when URLs contain brackets to disable glob parsingjq, environment variables may not expand correctly. Use Python examples instead.| Status | Meaning |
|--------|---------|
| 400 | Missing ElevenLabs connection or invalid request |
| 401 | Invalid or missing Maton API key |
| 403 | Insufficient permissions or quota exceeded |
| 422 | Invalid parameters |
| 429 | Rate limited |
| 4xx/5xx | Passthrough error from ElevenLabs API |
MATON_API_KEY environment variable is set:echo $MATON_API_KEYpython <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://ctrl.maton.ai/connections')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOFelevenlabs. For example:https://gateway.maton.ai/elevenlabs/v1/voiceshttps://gateway.maton.ai/v1/voicesGenerated Mar 1, 2026
Publishers can use this skill to convert manuscripts into audiobooks with natural-sounding voices, reducing production time and costs. It supports multiple languages and voice cloning for consistent narration across series.
Content creators can generate professional voiceovers for YouTube videos, tutorials, or advertisements without hiring voice actors. The streaming feature allows real-time audio generation for live or edited content.
Developers can integrate this skill into apps to provide text-to-speech for visually impaired users, enhancing accessibility in e-learning platforms or navigation systems. Timestamps enable synchronized audio with text highlights.
Businesses can create AI-powered customer service bots with cloned voices that sound like real agents, improving user engagement in call centers or chatbots. It processes audio for clear, lifelike responses.
Educational platforms can use this skill to generate pronunciation examples and dialogues in various accents, aiding language learners. Voice cloning allows customization for specific dialects or instructors.
Offer a cloud-based service where users pay monthly for access to ElevenLabs API features through the Maton gateway. Revenue comes from tiered plans based on usage limits, voice cloning credits, or premium voices.
Resell ElevenLabs API access by bundling it with other AI tools or services through the Maton platform. Charge markup fees per API call or offer custom packages for enterprises needing high-volume audio generation.
Provide white-labeled audio generation tools for businesses to integrate into their own products, such as e-learning platforms or media companies. Revenue is generated through licensing fees and setup costs.
💬 Integration Tip
Set the MATON_API_KEY environment variable and use the base URL for easy proxying; manage connections via the control panel for multi-account support.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
End-to-end encrypted agent-to-agent private messaging via Moltbook dead drops. Use when agents need to communicate privately, exchange secrets, or coordinate without human visibility.
Text-to-speech via OpenAI Audio Speech API.