Skip to main content

VocaBusta Voice API — Documentation

The VocaBusta Voice API gives any app lifelike African voices — the same engine that powers VocaBusta Studio. Generate speech in Nigerian Pidgin, Yoruba, Igbo, Hausa, Swahili and more; transcribe audio with the Vocabanga ASR model; clone a voice from a short clip; and dub videos into new languages while preserving each speaker.

Contents​

  1. Quickstart — your first request in 5 minutes
  2. Authentication — API keys and security
  3. Text to speech — synthesize audio from text
  4. Speech to text — transcribe audio with Vocabanga / Whisper
  5. Voice cloning — clone a voice from a short reference clip
  6. Dubbing — re-voice a video into a new language
  7. Voices & languages — the full voice catalog and language codes
  8. Rate limits & errors — quotas and error handling
  9. API reference — generated from the OpenAPI spec

Conventions​

  • Base URL: https://api.satryx.ai
  • All endpoints live under /voice (e.g. POST /voice/tts).
  • Auth — every call needs Authorization: Bearer satryx_live_… (or satryx_test_…). Generation endpoints also require an active VocaBusta subscription on the account. See Authentication.
  • JSON vs. multipart — text-only requests (TTS, dub translate) send JSON; anything that uploads a file (STT, cloning, dubbing) uses multipart/form-data.
  • Errors use FastAPI's envelope: { "detail": "human-readable message" } with a matching HTTP status. See Rate limits & errors.

SDKs​

The Satryx first-party SDKs wrap the whole platform (chat, images, and voice):

  • Python — pip install satryx
  • TypeScript / Node — npm install @satryx/sdk

Every example in these docs also shows the raw HTTP call, so you can use any language with an HTTP client.