RVC-Boss/GPT-SoVITSGitHub
choose for few-shot voice cloning from minimal data instead of full single-speaker training.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- 61.2k
- Python
- MIT
active2mo ago
jaywalnut310/vits Alternatives
text-to-speech (TTS)
VITS is a PyTorch implementation of an end-to-end text-to-speech model using conditional variational autoencoding and adversarial training to synthesize speech from text.
Same job, different approach
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
OpenBMB/VoxCPMGitHub
choose for multilingual tokenizer-free cloning and creative voice design, at higher compute cost.
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
- 36.0k
- Python
- Apache-2.0
active2mo ago
PaddlePaddle/PaddleSpeechGitHub
choose for a PaddlePaddle-based all-in-one speech toolkit rather than a standalone PyTorch TTS.
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.
- 12.7k
- Python
- Apache-2.0
active2mo ago
open-mmlab/AmphionGitHub
choose for a broader audio-generation research toolkit with TTS components, if you don't mind framework overhead.
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.
- 10.3k
- Python
- MIT
active6mo ago
espnet/espnetGitHub
choose for ESPnet research recipes covering TTS/ASR rather than a single-model implementation.
End-to-End Speech Processing Toolkit
- 9.9k
- Python
- Apache-2.0
active2mo ago
k2-fsa/OmniVoiceGitHub
choose for 600+ language voice cloning TTS, at higher model complexity.
High-Quality Voice Cloning TTS for 600+ Languages
- 9.3k
- Python
- Apache-2.0
active2mo ago
netease-youdao/EmotiVoiceGitHub
choose for prompt-controlled emotional multi-voice TTS; code is dormant but usable.
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
- 8.5k
- Python
- Apache-2.0
dormant2.1y ago
metavoiceio/metavoice-srcGitHub
choose for expressive large-model TTS with human-like prosody, trading runtime weight.
Foundational model for human-like, expressive TTS
- 4.2k
- Python
- Apache-2.0
dormant2.2y ago
Edresson/YourTTSGitHub
choose for zero-shot multi-speaker TTS and voice conversion, if your task needs both.
YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
- 1.1k
- Jupyter Notebook
- NOASSERTION
dormant1.9y ago
daniilrobnikov/vits2GitHub
choose for improved VITS-based quality/efficiency as a successor, but expect to adapt code.
VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design
- 647
- Jupyter Notebook
- MIT
dormant3.1y ago
yl4579/StyleTTS2GitHub
choose for style-controlled human-level TTS, at higher inference cost.
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
- 6.4k
- Python
- MIT
dormant2.2y ago
Aratako/Irodori-TTSGitHub
choose for emoji-driven style control with flow matching, if you want those specific controls.
A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
- 1.2k
- Python
- MIT
active2mo ago
Older generation, or narrower
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
CorentinJ/Real-Time-Voice-CloningGitHub
choose for real-time voice cloning from 5s audio, accepting stale unlicensed code.
Clone a voice in 5 seconds to generate arbitrary speech in real-time
- 60.1k
- Python
- NOASSERTION
active7mo ago
babysor/MockingBirdGitHub
choose for Chinese real-time voice cloning, accepting an older unmaintained codebase.
🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
- 36.9k
- Python
- NOASSERTION
active7mo ago
keonlee9420/DiffGAN-TTSGitHub
choose for diffusion GAN TTS research, but it is older and unmaintained.
PyTorch Implementation of DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs
- 349
- Python
- MIT
dormant4.6y ago
Tomiinek/Multilingual_Text_to_SpeechGitHub
choose for older Tacotron 2 multilingual TTS research, not for modern quality.
An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.
- 844
- Python
- MIT
archived3.0y ago
End-user tools
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
rhasspy/piperGitHub
choose for offline low-latency TTS on edge devices via standalone binary, not a training codebase.
A fast, local neural text to speech system
- 11.3k
- C++
- MIT
archived1.1y ago
Listed as an alternative to
These projects were analysed and named vits among their alternatives. The relationship is not symmetric — how vits rates them is a separate judgement, made when vits is analysed in its own right.
coqui-ai/TTSGitHub
calls vits “The reference implementation of the VITS model; pick it for a clean single-model baseline rather than a full library.”
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
45.9kPythondormant
espeak-ng/espeak-ngGitHub
calls vits “choose it for end-to-end neural TTS with a specific trained model, accepting the need for PyTorch and GPU.”
eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
6.8kCactive
ranchlai/mandarin-ttsGitHub
calls vits “Choose it for end-to-end VITS quality with a single-stage pipeline, accepting English-centric data and no maintenance.”
Chinese Mandarin tts text-to-speech 中文 (普通话) 语音 合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder, with biaobei and aishell3 datasets
477Pythondormant
supertone-inc/supertonicGitHub
calls vits “For a classic VITS model if you require the original architecture; it's older and not as fast as modern ONNX TTS.”
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
13.7kSwiftactive
PaddlePaddle/PaddleSpeechGitHub
calls vits “Reference implementation of VITS TTS; old, use for reproducing the paper.”
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.
12.7kPythonactive
open-mmlab/AmphionGitHub
calls vits “Choose only to reproduce the specific VITS model for end-to-end TTS; it is narrower and older than 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.
10.3kPythonactive
mozilla/TTSGitHub
calls vits “choose if you want the single VITS end-to-end model rather than a multi-model framework.”
:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
10.2kJupyter Notebookdormant
espnet/espnetGitHub
calls vits “Choose when you want the VITS architecture for TTS as a standalone model, instead of using ESPnet's integrated environment.”
End-to-End Speech Processing Toolkit
9.9kPythonactive
netease-youdao/EmotiVoiceGitHub
calls vits “choose to study the classic VITS architecture; too old for production.”
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
8.5kPythondormant
ZDisket/TensorVoxGitHub
calls vits “Choose if you want the original VITS training/inference code, but it's a single-model research repo.”
Desktop application for neural speech synthesis written in C++
214C++slowing