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.

text-to-speech audit speech-synthesis audio-synthesis music-generation voice-conversion vocoder emilia text-to-audio fastspeech2 vits audio-generation singing-voice-conversion vall-e audioldm naturalspeech2 maskgct

• Updated Mar 25, 2026
• Python

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

text-to-speech tts gpt transformer-architecture emotional-speech voice-clone vall-e

• Updated Feb 11, 2024
• Python

An unofficial PyTorch implementation of the audio LM VALL-E

text-to-speech pytorch tts valle vall-e audio-lm

• Updated May 10, 2023
• Python

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

text-to-speech tts valle in-context-learning large-language-models chatgpt vall-e

• Updated Sep 10, 2025
• Python

ChatGPT, GenerativeAI and LLMs Timeline

timeline agi transformer openai llama gpt copilot claude generative-models large-language-models llm midjourney stable-diffusion generative-ai chatgpt langchain chatgpt-api vall-e palm-e

• Updated May 19, 2024

OpenMusic: SOTA Text-to-music (TTM) Generation

ai music-generation mdt dit ai-music diffusion-models text-to-audio music-ai ai-music-generator music-ai-architectures hifi-gan text-to-music vall-e text-to-audio-ai audioldm diffusion-transformer ai-music-generation text-to-music-transformer

• Updated Jun 26, 2025
• Python

AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

audio music semantic text-to-speech tokenizer speech sound codec audio-codec gpt language-model self-supervised-learning text-to-music vall-e text-to-sound speech-language-model

• Updated Nov 10, 2026
• Python

An unofficial PyTorch implementation of VALL-E

text-to-speech pytorch tts vall-e audio-lm

• Updated Nov 4, 2026
• Python

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io

text-to-speech tts voice-cloning singing-voice-synthesis vall-e

• Updated Sep 21, 2023
• Python

Applying deep learning to translate animation and re-generate audio.

whisper transformer-architecture emotional-speech voice-clone speech-to-speech-translation vall-e

• Updated Dec 16, 2024
• Python

Unofficial PyTorch implementation of VALL-E: zero-shot text-to-speech and voice cloning using neural codec language models. Train and synthesize speech from text with a single reference audio.

python machine-learning voice speech tts speech-synthesis transformer autoregressive nar zero-shot voice-synthesis deep-learnin voice-cloning vall-e text-to-text neural-codec pytorchmencodec

• Updated Jan 30, 2026
• Python

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

text-to-speech tts valle in-context-learning large-language-models chatgpt vall-e

• Updated Mar 29, 2025
• Python

VALL-E-X の日本語ツール

ai tts vall-e

• Updated Feb 15, 2024
• Jupyter Notebook