Get started
APIs
Every AudicLabs API and whether it is available today.
| API | Id | Status | What it does |
|---|---|---|---|
| Noise Suppressor | noise-suppressor | Available | Remove background noise from speech, one file or up to 25 per call. |
| Speech to Text · Hindi | stt-hindi | On request | Transcribe Hindi speech with word-level timestamps. |
| Speech to Text · English | stt-english | On request | Transcribe English speech with word-level timestamps. |
| Speech to Text · Non-Indic Multilingual | stt-multilingual | On request | One model for languages beyond India, with automatic language detection. |
| Speech to Text · Indic Multilingual | stt-indic | On request | One model for Indian languages, with automatic language detection. |
| Voice Activity Detection | vad | On request | Precise speech and silence boundaries for segmenting long audio. |
| Speaker Diarization | diarization | On request | Split multi-speaker audio into labelled turns: who spoke, and when. |
| Text to Speech · English | tts-english | On request | Natural English speech from text, streamed as it renders. |
| Text to Speech · Hindi | tts-hindi | On request | Natural Hindi speech from text, streamed as it renders. |
| Text to Speech · Non-Indic Multilingual | tts-multilingual | On request | Speech in languages beyond India from one model. |
| Text to Speech · Indic Multilingual | tts-indic | On request | Speech in Indian languages from one model. |
| Speaker Recognition | speaker-recognition | On request | Enrol a voice once, then verify or identify the speaker from new audio. |
Getting access
APIs marked On request are enabled per workspace. Ask your workspace admin; once enabled, the API appears in the console and the API explorer with its endpoints, and its reference pages are added here.