The database of free AI tools on GitHub

Speech recognition model for multilingual transcription and translation.

Create and use cloned voices for various tasks locally.

Converts voice samples to text-to-speech models for various languages.

Clone a voice in real-time for generating speech.

Local AI voice studio for voice cloning and speech generation.

Port of OpenAI's Whisper model in C/C++

Generates natural dialogue-based speech for LLM assistants.

WebUI for training and using retrieval-based voice conversion models.

Clone voices for real-time text-to-speech generation.

Generate high-quality speech from text using advanced AI models.

Privacy-first AI meeting assistant for real-time transcription and summaries.

Remove vocals from audio files using deep neural networks.

Transcribes audio faster than OpenAI Whisper with CTranslate2.

Automatic speech recognition with word-level timestamps and speaker diarization.

Clones voices from single audio clips for text-to-speech.

Transcribes and translates audio offline using Whisper.

Open-source toolkit for speech recognition and ASR deployment.

Convert e-books to audiobooks with text-to-speech and voice cloning.

Translate videos and audio, add dubbing and subtitles.

Generates realistic dialogue from text with emotion control.

Automated video subtitle and dubbing tool with AI translation.

Build real-time voice and multimodal conversational agents.

Convert text to high-quality speech using CPU or GPU.

Create realistic AI avatars and videos offline with precise voice and appearance cloning.

Local speech recognition and synthesis for various platforms and programming languages.

Offline speech recognition for 20+ languages in various programming languages.

AI-powered speech recognition, translation, and voice cloning tool.

Speech recognition, translation, and text-to-speech toolkit.

Use Microsoft Edge's text-to-speech service from Python.

Build real-time voice agents and applications with low-latency speech recognition and text-to-speech.