Add speech generation to your website, app, CMS, media platform, LMS or internal product. The HancVoice REST API works with system and custom voices, voice creation, transcription and streaming speech.
Automatically create audio versions of publications, digests and long-reads.
Voice lessons, quizzes, hints and course updates without manual recording.
Voice notifications, IVR, assistants, instructions and personalized audio snippets.
The API covers the core path «text → WAV/MP3», streaming generation, the voice catalog, voice creation, transcription and engine health checks. No SDK promises: plain REST and ordinary HTTP requests. The API is available from the Starter plan and up; the text length per request is capped by your plan.
API access opens from the Starter plan. Request rate and length grow with your plan.
WAVMP3PCM stream10 languagessystem voicescustom voicesown voice creationtranscription
An API key is issued from the Starter plan and up. The request rate limit and text length per request depend on your plan — see the documentation for exact values.
WAV and MP3 for finished files, and PCM for streaming generation via /api/v1/tts_stream when a fast playback start matters.
Yes. POST /api/v1/tts_stream returns PCM as synthesis progresses — this reduces the time to first sound in voice interfaces and assistants.
Sign up, upgrade to the Starter plan or higher and create a key in your dashboard. Request examples and the full method reference are in the developer documentation.
Get an API key and test generation on your own texts.