Audio

Speech synthesis (text to speech) and transcription (speech to text).

Speech synthesis

http

POST /v1/audio/speech

json

{
  "text": "Bonjour, ceci est un test de synthese vocale.",
  "voice": "alloy",
  "model": null,
  "routing_strategy": "auto"
}

voice depends on the chosen provider: OpenAI voice names (alloy, echo, ...) and ElevenLabs voice IDs are not interchangeable — set model explicitly if you need a specific voice.

json

{
  "audio": "https://cdn.uploadscenter.com/file_...",
  "model": "eleven_multilingual_v2",
  "provider": "elevenlabs"
}

Transcription

http

POST /v1/audio/transcriptions

json

{
  "audio_url": "https://exemple.com/enregistrement.mp3",
  "language": "fr",
  "model": null,
  "routing_strategy": "auto"
}

json

{
  "text": "Transcription du contenu audio.",
  "model": "whisper-1",
  "provider": "openai"
}

Providers

OpenAI (TTS + Whisper), ElevenLabs (high-quality multilingual speech synthesis + transcription).