IIT Bombay Speech
IIT Bombay speech group — Indian-language ASR research and Bhashini contributions.
IIT Bombay speech group — Indian-language ASR research and Bhashini contributions.
Best for marathi, Gujarati, and other Indic-language transcription research projects. Pricing: free.
What it is
IIT Bombay's speech and language groups contribute to Bhashini and publish their own Indian-language ASR research, particularly on Marathi and Gujarati where the city's market is dense. Buyers should treat these releases as research baselines rather than production products, and engage Bhashini or commercial Indic vendors for production deployment. Best fit when the buyer is marathi, gujarati, and other indic-language transcription research projects. The honest caveat: academic outputs without commercial slas. As with any open-weights release, the integrator owns hosting, scaling, and SLA — but the licensing cost is zero and the model can be fine-tuned on in-house audio.
Watch out for: Academic outputs without commercial SLAs.
Install / use
cse.iitb.ac.in — group publications and model releases
Features
| Speaker diarization | No |
| Word-level timestamps | Yes |
| Streaming / real-time | No |
| Languages supported | None |
| HIPAA eligible | No |
IIT Bombay Speech vs Whipscribe
| Feature | IIT Bombay Speech | Whipscribe |
|---|---|---|
| Category | Open source | Transcription APIs |
| Pricing | free | free beta |
| Speaker diarization | No | Yes |
| Word timestamps | Yes | Yes |
| Streaming | No | No |
| Languages | — | 99 |
| Platforms | Linux | Web, API, MCP |
Alternatives to IIT Bombay Speech
Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.