nari-labs / dia
A TTS model capable of generating ultra-realistic dialogue in one pass.
Why this job: says: tts; topics: text-to-speech
What it does
- Generate dialogue via [S1] and [S2] tag
- Generate non-verbal like (laughs), (coughs), etc.
- Voice cloning. See example/voice_clone.py for more information.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Inactive
- Last commit 11 months ago
- Stars
- 19,410
- +9 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 62% closed
- 68 still open
- Pull requests
- 49 merged
- 23 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| ekwek1 / soprano | 1,635 | 10 months ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- ai
- open-weight
- text-to-speech
Project record
- JobSpeech and audio
- StatusListed
- Commits90
- Forks1,693
- Watching163
- Stars in 28 days+30
- CreatedApr 19, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026