SeamlessM4T
Meta's speech-to-text + speech-to-speech + text-to-speech model, 100 languages.
Meta's speech-to-text + speech-to-speech + text-to-speech model, 100 languages.
Best for cross-lingual transcription and translation in one model, especially low-resource languages. Pricing: free.
What it is
SeamlessM4T is Meta's "do everything with speech" foundation model. Good for projects that need transcription + translation in the same pass, particularly for languages Whisper covers poorly. Check the license — the research license rules out commercial deployment without separate permission.
Watch out for: Research license (non-commercial for v1); heavier runtime than Whisper; docs assume fairseq familiarity.
Install / use
pip install fairseq2 # then load SeamlessM4T v2Features
| Speaker diarization | No |
| Word-level timestamps | No |
| Streaming / real-time | Yes |
| Languages supported | 100 |
| HIPAA eligible | No |
Links
SeamlessM4T vs Whipscribe
| Feature | SeamlessM4T | Whipscribe |
|---|---|---|
| Category | Open source | Transcription APIs |
| Pricing | free | free beta |
| Speaker diarization | No | Yes |
| Word timestamps | No | Yes |
| Streaming | Yes | No |
| Languages | 100 | 99 |
| Platforms | Linux, GPU | Web, API, MCP |
Alternatives to SeamlessM4T
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.