open-mmlab / Amphion
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
Why this job: topics: text-to-speech, speech-synthesis, music-generation, audio-generation
What it does
- Vevo. A zero-shot voice imitation framework with controllable timbre and style. Vevo-Timbre conducts the style-preserved voice conversion, and Vevo-Voice conducts the style-converted voice conversion. [](models/vc/vevo/README.md)
- FACodec. FACodec decomposes speech into subspaces representing different attributes like content, prosody, and timbre. It can achieve zero-shot voice conversion. [](https://huggingface.co/amphion/naturalspeech3_facodec)
- Noro. A noise-robust zero-shot voice conversion system. Noro introduces innovative components tailored for VC using noisy reference speeches, including a dual-branch reference encoding module and a noise-agnostic contrastive speaker loss. [
- DualCodec, a low-frame-rate (12.5Hz or 25Hz), semantically-enhanced (with SSL feature) Neural Audio Codec designed to extract discrete tokens for efficient speech generation.[](http://arxiv.org/abs/2505.13000)[](https://colab.research.googl
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Inactive
- Last commit 7 months ago
- Stars
- 10,339
- +9 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.1.1-alpha
- Released 2 years ago
- Built with
- Python
- 50% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 49% closed
- 161 still open
- Pull requests
- 117 merged
- 17 waiting
- Releases
- 3
- 0 in the last year
- Contributing guide (opens in new tab)
- No security policy
- Code of conduct (opens in new tab)
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| OpenMOSS / MOSS-TTS | 4,321 | 2 months ago | Apache-2.0 | No downloads |
| denizsafak / abogen | 6,223 | 11 days ago | MIT | No downloads |
| IAHispano / Applio | 3,992 | 8 days ago | MIT | No downloads |
More: languages, topics, project record and preview image
Languages
- Python 50%
- Jupyter Notebook 47%
- JavaScript 1%
- Shell 1%
Topics
- audio-generation
- audio-synthesis
- audioldm
- music-generation
- naturalspeech2
- singing-voice-conversion
- speech-synthesis
- text-to-audio
- text-to-speech
- vall-e
- voice-conversion
- audit
Project record
- JobSpeech and audio
- StatusListed
- Commits126
- Forks858
- Watching89
- Stars in 28 days+39
- CreatedNov 15, 2023
- First seen by usNov 7, 2026
- CheckedNov 8, 2026