html5 js 录音 mp3 wav ogg webm amr g711a g711u 格式，支持pc和Android、iOS部分Web浏览器、Hybrid App（提供Android iOS App源码）、微信，提供ASR语音识别转文字 H5版语音通话聊天示例 DTMF编码解码
$ git clone https://github.com/xiangyuecn/Recorder.git▲ +64 ★ this week
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
▲ +11 ★ this week
A PyTorch-based Speech Toolkit
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.
Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
▲ +12 ★ this week
Controllable Transcription. Verbatim ( every, filler, pause, stutter, vocal sound) , or intended ( what the speaker meant to say, optimized for readability) with word-level timestamps.
SincNet is a neural architecture for efficiently processing raw audio samples.
Data from GitHub · snapshot Nov 13, 2026