opendilab / CleanS2S
High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！
Why this job: topics: speech-recognition, speech-synthesis
What it does
- Full-duplex interaction with interruptions
- Complemented with Web Search and RAG
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Inactive
- Last commit 7 months ago
- Stars
- 544
- +1 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
- 62% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 93% closed
- 2 still open
- Pull requests
- 12 merged
- 2 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Neywa-Labs / mlx-audio | 8,251 | yesterday | MIT | No downloads |
| vndee / local-talking-llm | 896 | 7 months ago | MIT | No downloads |
| soniqo / speech-swift | 1,271 | 2 days ago | Apache-2.0 | Mac |
More: languages, topics and project record
Languages
- Python 62%
- TypeScript 37%
- CSS <1%
- JavaScript <1%
Topics
- ai
- gpt-4o
- machine-learning
- python
- speech-recognition
- speech-synthesis
- speech-to-speech
- streaming
Project record
- JobSpeech and audio
- StatusListed
- Commits53
- Forks54
- Watching7
- Stars in 28 days+2
- CreatedSep 26, 2024
- First seen by usNov 7, 2026
- CheckedNov 8, 2026