Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Speech recognition, text-to-speech, voice cloning, music generation and audio processing.
Signals: speech-recognition, text-to-speech, tts, stt, asr, whisper, voice-cloning, speech-synthesis
910 results
Free and open source text-to-speech software
Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!
StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
实时交互数字人，可自定义形象与音色，支持音色克隆，对话延迟低至3s。Real-time voice interactive digital human, customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.
Soprano: Instant, Ultra-Realistic Text-to-Speech
General Speech Restoration
一个可以录制 Microsoft Edge 浏览器的语音合成（TTS）语音并输出为 .wav 音频的（windows平台）工具。
Interface for OuteTTS models.
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
[AutoArk] GPA (General Purpose Audio) can do ASR, TTS and voice conversion with one tiny model!
Automatically translates the text of a video based on a subtitle file, and then uses AI voice services to create a new dubbed & translated audio track where the speech is synced using the subtitle's timings.
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model
Text-To-Speech, RAG, and LLMs. All local!
PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models
Free, high-quality text-to-speech API endpoint to replace OpenAI, Azure, or ElevenLabs
WaveRNN Vocoder + TTS
Controllable and fast Text-to-Speech for over 7000 languages!
PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html
开源文本转语音工具，支持超长文本，多角色配音
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
MARY TTS -- an open-source, multilingual text-to-speech synthesis system written in pure java
🤖️ Cross-platform AI language practice app （跨平台AI语言练习应用）
Python library and CLI tool to interface with Google Translate's text-to-speech API
aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)
24,535 repositories in the index in total.
