i ideas / repo launcher
coqui-ai avatar

coqui-ai/TTS

โ˜… 46,215PythonMPL-2.068

๐Ÿธ๐Ÿ’ฌ - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

What it is

๐Ÿ“ฃ โ“TTSv2 is here with 16 languages and better performance across the board. ๐Ÿ“ฃ โ“TTS fine-tuning code is out. Check the example recipes. ๐Ÿ“ฃ โ“TTS can now stream with ๐Ÿ› ๏ธ Tools for training new models and fine-tuning existing models in any language. Please use our dedicated channels for questions and discussion. Help is much more valuable if it's shared publicly so that more people can benefit from it.

When to use it

Reach for TTS when your project generates or processes images, video, speech or audio โ€” it's written in Python and fits stacks tagged deep-learning, glow-tts, hifigan, melgan.

Category
Generative Media
Also in
โ€”
Stars
46,215
Forks
6,162
Last push
2.2 years ago
Created
2020-05-20
Open issues
2
Website
coqui.ai
#deep-learning#glow-tts#hifigan#melgan#multi-speaker-tts#python#pytorch#speaker-encoder#speaker-encodings#speech#speech-synthesis#tacotron#tts#tts-model

Quick start

$ git clone https://github.com/coqui-ai/TTS.git

Hand it to your AI

Read https://ideas.asveas.com/r/coqui-ai/TTS.md and help me add coqui-ai/TTS to my project. Explain the setup steps for my stack and show the minimal code to get it working.
Generative MediaMarkdown .mdOpen on GitHub โ†ต

Alternatives to TTS

All Generative Media โ†’
yt-dlp avataryt-dlpA feature-rich command-line audio/video downloaderโ˜… 207kComfy-Org avatarComfyUIThe most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.โ˜… 146kremotion-dev avatarremotion๐ŸŽฅ Make videos programmatically with Reactโ˜… 72.5kggml-org avatarwhisper.cppPort of OpenAI's Whisper model in C/C++โ˜… 55.1klemomo-ai avatarlemo-opuscarA toolbox of film styles made in code for Claude Code: 66 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by Claude Opus 5.5, with no video model. By Lemomo. ยท ไธ€ๅฅ—็”จไปฃ็ ๅš็‰‡็š„้ฃŽๆ ผๅทฅๅ…ท็ฎฑ๏ผš66 ็ง็Žฐๆˆ้ฃŽๆ ผ๏ผŒไนŸ่ƒฝๅšๅ‡บไฝ ่‡ชๅทฑ็š„โ˜… 14.8kopenai avatarwhisperRobust Speech Recognition via Large-Scale Weak Supervisionโ˜… 112k

Pairs well with

huggingface avatartransformers๐Ÿค— Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.โ˜… 169kAUTOMATIC1111 avatarstable-diffusion-webuiStable Diffusion web UIโ˜… 165kunslothai avatarunslothLocal UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.โ˜… 79.3kstreamlit avatarstreamlitStreamlit โ€” A faster way to build and share data apps.โ˜… 46.3kgradio-app avatargradioBuild and share delightful machine learning apps, all in Python. ๐ŸŒŸ Star to support our work!โ˜… 44kpydantic avatarpydantic-aiHow Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.โ˜… 21.1k

FAQ

What is TTS?

coqui-ai/TTS is a media tool on GitHub: ๐Ÿธ๐Ÿ’ฌ - a deep learning toolkit for Text-to-Speech, battle-tested in research and production ๐Ÿ“ฃ โ“TTSv2 is here with 16 languages and better performance across the board.

When should I use TTS?

Reach for TTS when your project generates or processes images, video, speech or audio โ€” it's written in Python and fits stacks tagged deep-learning, glow-tts, hifigan, melgan.

What are the best alternatives to TTS?

Popular alternatives in Generative Media: yt-dlp/yt-dlp (207kโ˜…), Comfy-Org/ComfyUI (146kโ˜…), remotion-dev/remotion (72.5kโ˜…), ggml-org/whisper.cpp (55.1kโ˜…), lemomo-ai/lemo-opuscar (14.8kโ˜…).

Is TTS actively maintained?

coqui-ai/TTS looks quiet โ€” no recent pushes: the last push was 2.2 years ago (2024-08-16), with 46,215 stars and 2 open issues.

What license does TTS use?

coqui-ai/TTS is published under the MPL-2.0 license. Check the repository's LICENSE file before commercial use.