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.
This toolkit helps audio researchers and developers create realistic generated audio for speech, music, and singing. It takes text, existing voices, or other audio inputs and produces synthetic audio outputs like spoken sentences, songs, or instrumentals. It's designed for junior researchers and engineers working on audio generation models.
9,712 stars. No commits in the last 6 months.
Use this if you are a researcher or engineer looking to develop, experiment with, and evaluate models for generating audio, music, or speech.
Not ideal if you are an end-user simply looking for a ready-to-use application to generate audio without getting involved in model development.
Stars
9,712
Forks
796
Language
Python
License
MIT
Category
Last pushed
May 27, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/open-mmlab/Amphion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
whitphx/streamlit-stt-app
Real time web based Speech-to-Text app with Streamlit
saidsef/tika-document-to-text
Apache Tika extract text and metadata from any document format with this pre-built containerised...
declare-lab/jamify
JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment
SiddhantSadangi/st_deepgram_playground
API playground for Deepgram built with Streamlit
hipnologo/EchoForge_Studio
Multi-LLM writing and voice production workspace built with Streamlit.