tts-production

TTS Production with ElevenLabs

Generate, audition and mix narration using the ElevenLabs Text-to-Speech API. Model guidance was checked on 2026-10-07 against the official ElevenLabs TTS skill and models documentation; re-check the live endpoint, voice eligibility, quota and price before execution.

This skill uses the official HTTP API; inspect the actual schema if an optional connector is used. Use narration audition for spoken phrasing, delivery and the audition decision. Keep voice identifiers and account receipts in the private execution record.

API Pattern

Text-to-Speech with Timestamps (recommended)

curl --fail-with-body -sS -X POST "https://api.elevenlabs.io/v1/text-to-speech/${VOICE_ID}/with-timestamps" \
  -H "xi-api-key: ${ELEVENLABS_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Your text here",
    "model_id": "eleven_v4",
    "voice_settings": {
      "stability": 0.75,
      "similarity_boost": 0.80
    }
  }' \
  --output /tmp/tts-response.json

Decode Response

import json, base64
with open('/tmp/tts-response.json', 'r') as f:
    data = json.load(f)
audio_bytes = base64.b64decode(data['audio_base64'])
with open('output.mp3', 'wb') as f:
    f.write(audio_bytes)
ends = data.get('alignment', {}).get('character_end_times_seconds', [])
print(f'Duration: {ends[-1]:.2f}s' if ends else 'No timestamps')

Simple TTS (no timestamps)

curl --fail-with-body -sS -X POST "https://api.elevenlabs.io/v1/text-to-speech/${VOICE_ID}" \
  -H "xi-api-key: ${ELEVENLABS_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{ "text": "Your text here", "model_id": "eleven_v4", "voice_settings": { "stability": 0.75, "similarity_boost": 0.80 } }' \
  --output output.mp3

Sound Effects Generation