The database of free AI tools on GitHub

Real-time speech-to-text with speaker diarization and translation.

Run AI locally on various devices with one SDK.

Generates audio, music, and speech from text and other inputs.

End-to-end speech processing toolkit for recognition, synthesis, and more.

Privacy-first voice-to-text dictation app with local and cloud models.

Multilingual text-to-speech using BERT and VITS2 backbone.

Convert e-books to audiobooks using text-to-speech models.

Generate text-to-speech with emotional control and multiple voices.

A deep-learning-based Chinese speech recognition system.

Transcribe audio and video locally with AI models.

提供本地网页界面和API，将文字合成为语音。

Convert text to speech across multiple languages.

Transforms text, images, and videos into multilingual audio conversations.

AI-powered video transcription and subtitle generation with LLM assistance.

End-to-end speech recognition toolkit in C++.

On-device speech recognition and text-to-speech for Apple Silicon.

Generate human-like speech using LLMs for text-to-speech.

Create and interact with AI characters in real-time using LLMs and voice cloning.

Convert text to high-quality audio with synchronized subtitles.

Provides pre-trained text-to-speech models for various languages.

一站式开源工具，实现视频转字幕、翻译、配音与合成。

AI工具用于视频的本地化和配音，包括语音识别、翻译和语音合成。

Automatically transcribes and diarizes audio using OpenAI Whisper.

Dockerized FastAPI wrapper for text-to-speech with multi-speaker support and custom voicepacks.

End-to-end speech recognition toolkit for production use.

Detects wake words on-device for voice-enabled applications.

Synthesize singing and speech voices using diffusion models.

离线语音识别转文字工具，支持多种语言和模型。

Real-time audio and video communication library for Python.

Real-time voice AI agent built on Ultravox LLM.