huggingface / speech-to-speech
Build voice agents with open-source models
Why this job: topics: speech-to-text, speech-synthesis
What it does
A low-latency voice agent built from open models that runs entirely on your computer. One command starts a conversation: no API key, no cloud service.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 4 days ago
- Stars
- 13,665
- +39 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.1.0
- Released 17 days ago
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 9
- Last 90 days
- Issues
- 87% closed
- 35 still open
- Pull requests
- 414 merged
- 35 waiting
- Releases
- 6
- 6 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| NVIDIA-NeMo / Speech | 18,721 | yesterday | Apache-2.0 | No downloads |
| Migushthe2nd / MsEdgeTTS | 347 | 16 days ago | MIT | No downloads |
| netease-youdao / EmotiVoice | 8,541 | 2 months ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
- Dockerfile <1%
- Shell <1%
Topics
- ai
- assistant
- language-model
- machine-learning
- python
- speech
- speech-synthesis
- speech-to-text
- speech-translation
Project record
- JobSpeech and audio
- StatusListed
- Commits1,693
- Forks1,690
- Watching80
- Stars in 28 days+264
- CreatedAug 7, 2024
- First seen by usNov 7, 2026
- CheckedNov 10, 2026