audio/speech generation toolkit
Amphion is an open-source toolkit for audio, music, and speech generation, supporting tasks like TTS, SVS, VC, SVC, and TTA, with visualizations and multiple models.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose when you need a focused few-shot voice cloning TTS with active development, while Amphion is a broader research toolkit.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Choose when you want a classic, lightweight voice cloning pipeline, though it is older than Amphion's integrated approaches.
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Choose when you need a modern multilingual TTS with creative voice design and cloning as a standalone model.
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
Choose when you need a full speech toolkit including ASR and translation alongside TTS, from the PaddlePaddle ecosystem.
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
Choose when you need a mature, all-in-one speech processing toolkit with extensive recipes and research models, similar to Amphion.
End-to-End Speech Processing Toolkit
Choose when you need low-resource voice cloning TTS across many languages.
High-Quality Voice Cloning TTS for 600+ Languages
Choose when you need a production-tested TTS toolkit with many models, though it does not cover music/audio generation like Amphion.
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Choose when you need a straightforward voice cloning TTS as a simple baseline, similar to Real-Time-Voice-Cloning.
🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
Choose when you need a prompt-controlled multi-voice TTS engine, though it is not updated recently.
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
Choose when you need zero-shot multi-speaker TTS and voice conversion from a single model, still relevant.
YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
Choose when you want a unified audio processing and generation toolkit from Alibaba, covering multiple tasks.
An Open-Source Project to Unify Audio Processing and Generation
Choose when you need a state-of-the-art singing voice synthesis model with diffusion, as an alternative to Amphion's SVS.
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code
Choose when you need a pure C++ inference engine for audio models without Python dependencies, ideal for lightweight deployment.
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Choose when you need an older foundational TTS model for expressive speech, but it is not actively maintained.
Foundational model for human-like, expressive TTS
Choose when you need a fast, offline, lightweight C++ TTS engine, but it is archived and limited in scope.
A fast, local neural text to speech system
Choose only to reproduce the specific VITS model for end-to-end TTS; it is narrower and older than Amphion.
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
Choose only to reproduce the DiffGAN-TTS paper; it is an older TTS implementation.
PyTorch Implementation of DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs
Choose when you need a singing voice conversion model, but it is archived and superseded.
SoftVC VITS Singing Voice Conversion
Choose when you need real-time zero-shot voice conversion/singing voice conversion, but it is archived.
zero-shot voice conversion & singing voice conversion, with real-time support
Choose when you need an older singing voice conversion implementation using VITS; it is narrow and not maintained.
Core Engine of Singing Voice Conversion & Singing Voice Clone
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
Choose when you want to deploy a TTS server with a Web UI and API, not a development toolkit.
Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale text processing. Runs accelerated on NVIDIA (CUDA), AMD (ROCm), and CPU.
These projects were analysed and named Amphion among their alternatives. The relationship is not symmetric — how Amphion rates them is a separate judgement, made when Amphion is analysed in its own right.
calls Amphion “An audio, music, and speech generation toolkit; choose it for broad research flexibility beyond just TTS.”
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
calls Amphion “Choose when you need a unified toolkit covering TTS/SVS in addition to music, with a more modular architecture.”
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
calls Amphion “Choose when you need a research toolkit to experiment with multiple speech-generation approaches including zero-shot TTS.”
🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
calls Amphion “Choose for a research toolkit covering many audio generation methods, not just TTS.”
SoTA open-source TTS
calls Amphion “choose for a maintained audio/music/speech generation toolkit with reproducible research instead of seed's speech examples.”
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
calls Amphion “choose it when you need a broad research toolkit covering audio/music/speech generation rather than a single optimized music model”
The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
calls Amphion “Choose when you are doing research or building custom audio generation and need a flexible toolkit.”
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key
calls Amphion “choose for reproducible audio research; not as a drop-in TTS API.”
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
calls Amphion “choose for a broader audio-generation research toolkit with TTS components, if you don't mind framework overhead.”
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
calls Amphion “Research toolkit for audio/speech generation, includes TTS models; pick it for reproducible experiments rather than a simple library.”
High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.
calls Amphion “Choose for a broad Python audio/speech generation toolkit if you need training and research flexibility.”
Desktop application for neural speech synthesis written in C++
calls Amphion “An audio/music/speech-generation toolkit; choose it for an audio-only pipeline, but it lacks image and video diffusion support.”
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
calls Amphion “Audio/music/speech generation toolkit, no ASR; choose for synthesis research and production.”
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
calls Amphion “Choose when you focus solely on audio/music/speech generation and want a research toolkit for that subset, not recognition.”
End-to-End Speech Processing Toolkit
calls Amphion “Choose when you need a research toolkit for audio/music/speech generation and want PyTorch flexibility.”
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.