Documentation for kokoro-82m

Performs Text-to-Speech (TTS) synthesis using the /api/v1/tts endpoint. This specific model (kokoro-82m) is used internally by the service when this endpoint is called, based on system configuration.

The endpoint accepts text and an optional voice ID to generate audio. Refer to the full documentation for the /api/v1/tts endpoint for details on headers, parameters (voice), error handling, and the WAV audio stream response format.

Sample Request (cURL)

# Replace <your-orchestrator-host> and <API_KEY> with your actual values
# The specific model (kokoro-82m) is typically selected by the backend for this endpoint.
curl https://<your-orchestrator-host>/api/v1/tts \
  -H "Authorization: Bearer <API_KEY>" \
  -H "X-User-Id: your_user_id_123" \
  -H "Content-Type: application/json" \
  --output speech_output.wav \
  -d '{
        "text": "Hello from the decentralized network! This audio was generated using Kokoro.",
        "voice": "af_nicole" # Optional: See endpoint docs for available voices
      }'