Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
- pytorch
- speech-recognition
- paraformer
- punctuation
99,825 visible repositories in the index
1–24 of 37 · Most stars
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.
Foundational Models for State-of-the-Art Speech and Text Translation
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
TranslatedOpen-source AI video localization and dubbing for YouTube/Bilibili: speech recognition, subtitle translation, voice cloning, audio mixing and rendering. Open-source AI video translation and dubbing tool.
TranslatedAIGCPanel is a simple and easy-to-use one-stop AI digital human system that supports video synthesis, voice synthesis, and voice cloning, and simplifies local model management, with one-click import and use of AI models.
A small speech recognizer
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
Speakr is a personal, self-hosted web application designed for transcribing audio recordings
Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.
HeartMuLa Official Repo: The Most Powerful Open-Source Music Generation Model of 2026
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
Transcribe and summarize videos and podcasts using AI. Open-source, multi-platform, and supports multiple languages.
Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
Translated知了 (Zhiliao, "cicada") Cicada · Live subtitles, interpreting and meeting notes for any call or stream, on Mac, Windows, Linux and Android. Free and open source.
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
A 0.9B model for long-form transcription in 50+ languages with speaker diarization, timestamps, and acoustic event awareness
Open-source local AI audio & music studio for macOS & Windows. TTS, voice cloning, songs with lyrics, and multi-track scores — 100% offline, zero API fees.
Generate text, images, video, speech, and music by MiniMax.