open-mmlab/Amphion

Health v2 · maintenance only

Adoption not part of the score

10271 stars · 847 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Amphion is an open-source Python toolkit for audio, music, and speech generation, supporting tasks like text-to-speech, voice conversion, singing voice conversion, and text-to-audio. It emphasizes reproducible research and includes visualizations of classic model architectures to help junior researchers learn the field.

Use cases

• generate speech from text with tts models
• convert one voice to another
• convert singing voice between singers
• generate audio or music from text descriptions
• train or evaluate vocoders
• reproduce research on speech generation models
• learn how tts and audio generation architectures work

When to choose

• you need a reproducible research platform for speech or audio generation
• you want implementations of models like VALL-E, NaturalSpeech2, FastSpeech2, or VITS
• you are a junior researcher learning audio generation with visualized architectures
• you need vocoders and evaluation metrics bundled with generation models

When to avoid

• you need a production-ready, low-latency tts service for end users
• you only want a simple pretrained model API without training pipelines
• you work outside audio, music, or speech domains

Facets

library · maturity active

tts audio-processing machine-learning deep-learning speech-recognition llm-training speech-processing machine-learning deep-learning python text-to-speech voice-conversion singing-voice-conversion text-to-audio text-to-music vocoder audio-generation research-toolkit speech-synthesis model-visualization audio natural-language-processing linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="open-mmlab/Amphion")