Back to Developer

API Docs

Pick the API you want to integrate with. All APIs share the same Bearer-token auth, credit pool, and job queue.

Text-to-Speech

Plain text in → rendered audio out. Single voice, no extras.

  • ·POST /api/tts/create — submit text
  • ·GET /api/tts/jobs/:jobId — poll status, get signed audioUrl
  • ·GET /api/tts/jobs — list all TTS jobs
Best for: Short narrations, notifications, voiceovers, programmatic TTS.

Speech-to-Text

Audio file in → transcript out. Segments + per-word timestamps.

  • ·POST /api/stt/create — upload audio (multipart)
  • ·GET /api/stt/jobs/:jobId — poll status, get transcript
  • ·Auto language detection, any file length
Best for: Transcription, captions/subtitles, read-along sync, searchable audio.

Audiobook

Full production: multi-voice, portraits, scenes, music, library entry.

  • ·File upload (EPUB, PDF, DOCX, TXT, AZW3)
  • ·AI character detection + voice casting
  • ·Portrait / scene / read-along batches
  • ·Bedtime stories & lullabies
Best for: Full-length books, rich productions, published library content.