#5050th of 51 in VoiceFor voice, speech and music
amphion
PyTorch toolkit for training and running speech, singing and audio generation models
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 10.3k
- License
- MIT
- Last commit
- Mar 2026
- Last release
- Feb 2024
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Amphion is a research toolkit with recipes and pretrained checkpoints for text-to-speech, voice conversion, accent conversion, singing voice conversion and text-to-audio. It includes models such as FastSpeech2, VITS, VALL-E, MaskGCT, Vevo and DualCodec, plus several vocoders and evaluation metrics. It also ships the Emilia multilingual speech dataset and its preprocessing pipeline.
Who it is for: Speech and audio researchers training or reproducing generation models
Strengths
- Covers TTS, VC, AC, SVC and TTA in one codebase with per-task recipes
- Includes many vocoders (HiFi-GAN, BigVGAN, DiffWave, WaveNet) and evaluation metrics
- Pretrained checkpoints on Hugging Face and ModelScope, including MaskGCT, Vevo and Metis
- Releases the Emilia dataset (over 200k hours with Emilia-Large) and its preprocessing pipeline
Weaknesses
- Research-oriented; no packaged end-user app or server API in the README
- Last tagged release is 2024-02-23, though commits continue
- Text-to-music is listed as still in development
- Emilia original data is CC BY-NC 4.0, unlike the MIT code
What it needs
- Docker
- Needs PyTorch
- Models: FastSpeech2, VITS, VALL-E, NaturalSpeech2, MaskGCT
Also in Voice
See all 51| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing and dictation with local speech models | 83 out of 100 |
| 2 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 80 out of 100 |
| 3 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 78 out of 100 |
| #4 | VoiceboxLocal voice studio for cloning, TTS, dictation and agent speech | 71 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 71 out of 100 |