No. 18 of 215 ·Text-to-Speech Software

Amphion

Linux · Self-hosted

Freedom report

Two barsScore 6.4

Free tierA free tier is on its own pricing page
Open codeNo open-source code on record
Runs widely1 of 6 device platforms
DocumentedPlans, terms and facts published

Amphion is ranked #18 of 215 in text-to-speech software on Freedom251. It runs on Linux, Self-hosted. There is a free plan.

Amphion plans and pricing

All plans

Amphion Free MIT-licensed · free for research and commercial use github.com · 5 Oct 2026

Compared on text-to-speech software

Free plan: Yes
Voice cloning: Yes
Audio upload formats: WAV, MP3, FLAC
Export formats: WAV

Best Amphion alternatives

See all 20

Two bars Voice.ai Free tier No. 1$5/mo6.7 Two bars Voicebox Free tier No. 2$1/mo6.7 Two bars Fish Audio Free tier No. 3$11/mo6.6 Two bars Kokoro TTS Free tier No. 4Free6.6 Two bars Speechify Free tier No. 5$29/mo6.6 Two bars TTSReader Free tier No. 6$10/mo6.6

The record

Purpose: Amphion is an open-source toolkit for audio, music, and speech generation aimed at supporting reproducible research and helping junior researchers and engineers get started.
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.
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.
Singing generation: Vevo2 supports controllable speech and singing generation, including voice conversion, singing voice conversion, singing voice editing, singing style conversion, and melody control.
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.
Audio evaluation: It provides objective evaluation metrics for F0 and energy modeling, intelligibility, spectrogram distortion, and speaker similarity.
Visualization: Amphion includes interactive visualizations of classic model processing, including SingVisio for the diffusion model used in singing voice conversion.
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.
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.
Installation: The README documents setup using Python 3.9.15 with Conda or a Docker image, and the Docker instructions require mounting the dataset into the container.
License and cost: Amphion is licensed under MIT and the README says it is free for research and commercial use.
Support and community: The project invites contributions and links to a Discord channel for community engagement.
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.
Datasets: Amphion unifies preprocessing for several open-source datasets and supports the Emilia dataset and Emilia-Pipe for in-the-wild speech data.
Price from: Free

Where it ranks on Freedom251

Best Text-to-Speech Software in 2026#18 of 215
Best AI Voice Conversion Software in 2026#5 of 28

Is Amphion yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote Amphion

Sources

github.com/open-mmlab/Amphion· checked 4 Oct 2026