Amphion
Amphion is a free, MIT-licensed toolkit for generating audio, music, and speech, aimed at reproducible research and helping junior researchers and engineers …
What Amphion is
Amphion is a free, MIT-licensed toolkit for generating audio, music, and speech, aimed at reproducible research and helping junior researchers and engineers get started. It supports text-to-speech, singing voice synthesis, voice conversion, accent conversion, singing voice conversion, and text-to-audio; text-to-music is still in development. Its model implementations span diffusion, transformer, VAE, and flow-based architectures. The toolkit includes speech models such as FastSpeech2, VITS, VALL-E, NaturalSpeech2, MaskGCT, and Vevo-TTS, plus voice conversion models including Vevo, FACodec, and Noro. Vevo2 supports controllable speech and singing generation, including voice conversion, singing voice editing, singing style conversion, and melody control. Amphion also provides audio evaluation metrics, interactive model visualizations, and preprocessing for multiple open-source datasets, including Emilia and Emilia-Pipe. Installation guidance documents Python 3.9.15 with Conda or Docker. Docker setup calls for NVIDIA drivers, NVIDIA Container Toolkit, and CUDA, and requires mounting the dataset into the container. WAV is listed as an export format.
Good
- Free for research and commercial use under the MIT License.
- Supports text-to-speech, singing, voice conversion, and text-to-audio.
- Includes audio evaluation metrics and interactive visualizations.
- Unifies preprocessing for multiple open-source datasets.
Watch out
- Text-to-music is still in development.
- Docker setup requires NVIDIA drivers, NVIDIA Container Toolkit, and CUDA.
- Dataset mounting is required for Docker setup.
Who it suits
Amphion suits researchers and engineers working on audio, music, or speech generation who want an open-source toolkit. Its Linux and self-hosted setup is relevant for users prepared to handle the documented installation requirements.
Verdict
Amphion covers several speech and audio generation tasks and includes research-oriented evaluation and dataset tools. Text-to-music is not yet supported, and its Docker setup has specific NVIDIA and dataset requirements.
Plans and prices
From Amphion's own pricing page, checked 5 Oct 2026.
| Plan | Price | What it gives you |
|---|---|---|
| Amphion | Free | MIT-licensed · free for research and commercial use |
The facts
Each one read from Amphion's own pages, with the date it was checked.
What it does
- Audio evaluation
- Its evaluation metrics cover F0 and energy modeling, intelligibility, spectrogram distortion, and speaker similarity.checked 5 Oct 2026
- Dataset preprocessing
- It unifies preprocessing for multiple open-source audio datasets and supports the Emilia dataset and Emilia-Pipe pipeline for in-the-wild speech data.checked 4 Oct 2026
- Datasets
- Amphion unifies preprocessing for several open-source datasets and supports the Emilia dataset and Emilia-Pipe for in-the-wild speech data.checked 5 Oct 2026
- Docker requirement
- The Docker instructions call for Docker, an NVIDIA Driver, NVIDIA Container Toolkit, and CUDA, and state that mounting the dataset with -v is necessary.checked 5 Oct 2026
- Export formats
- WAVchecked 20 Sep 2026
- External model tools
- For content-based features, the README lists pretrained models including WeNet, Whisper, and ContentVec.checked 5 Oct 2026
- Generation tasks
- Supported tasks include text-to-speech, singing voice synthesis, voice conversion, accent conversion, singing voice conversion, and text-to-audio; text-to-music is listed as in development.checked 4 Oct 2026
- Installation
- The README documents installation with a setup installer using Python 3.9.15 and with a Docker image.checked 5 Oct 2026
- Integrations and dependencies
- The project lists WeNet, Whisper, and ContentVec among pretrained models used for content-based features, and its Docker instructions require NVIDIA drivers, NVIDIA Container Toolkit, and CUDA.checked 4 Oct 2026
- Intended users
- The project describes itself as supporting reproducible research and helping junior researchers and engineers enter audio, music, and speech generation research and development.checked 5 Oct 2026
- License
- Amphion is released under the MIT License and is stated to be free for research and commercial use.checked 5 Oct 2026
- Models
- The toolkit implements diffusion, transformer, VAE, and flow-based model architectures.checked 5 Oct 2026
- Purpose
- Amphion is an open-source toolkit for audio, music, and speech generation intended to support reproducible research and help junior researchers and engineers get started.checked 5 Oct 2026
- Singing generation
- Vevo2 supports controllable speech and singing generation, including voice conversion, singing voice conversion, singing voice editing, singing style conversion, and melody control.checked 4 Oct 2026
- Support and community
- The project invites contributions and links to a Discord channel for community engagement.checked 4 Oct 2026
- Supported tasks
- The README marks text-to-speech, singing voice synthesis, voice conversion, accent conversion, singing voice conversion, and text-to-audio as supported, while text-to-music is in development.checked 5 Oct 2026
- Technical limit
- Text-to-music is listed as in development rather than supported.checked 5 Oct 2026
- Text to audio
- Amphion supports text-to-audio generation using a latent diffusion model and describes it as the official implementation of the text-to-audio generation part of its NeurIPS 2023 paper.checked 4 Oct 2026
- Visualization
- Amphion provides interactive visualizations of classic models and currently supports SingVisio for visualizing the diffusion model for singing voice conversion.checked 5 Oct 2026
- Voice and speech models
- The toolkit includes architectures such as FastSpeech2, VITS, VALL-E, NaturalSpeech2, MaskGCT, and Vevo-TTS for text-to-speech, plus Vevo, FACodec, and Noro for voice conversion.checked 4 Oct 2026
- Voice cloning
- Yeschecked 20 Sep 2026
Money
- Free plan
- Yeschecked 20 Sep 2026
- License and cost
- Amphion is licensed under MIT and the README says it is free for research and commercial use.checked 4 Oct 2026
Alternatives to Amphion
- 1
Voicebox
Free planOpen sourceAndroidiOSWebAPI9.3From $12 a year - 2
Speechify
Free planAndroidiOSWebAPI9.0From $10 a month - 3
Resemble AI
Free planAndroidiOSWebAPI9.0From $280 a month - 4
iSpeech
Free planOpen sourceAndroidiOSWebAPI9.0Free plan - 5
Fliki
Free planAndroidiOSWebAPI8.8From $28 a month - 6
Voice.ai
Free planAndroidiOSWebAPI8.8From $5 a month