Running
Agents
46
Automatic Speech Recognition
🌍
Transcribe audio files to text with Next‑gen Kaldi
FSA/FST algorithms, differentiable, with PyTorch compatibility. Automatic speech recognition
Transcribe audio files to text with Next‑gen Kaldi
Text-to-speech (TTS) with Next-gen Kaldi
ZipVoice voice cloning
Pocket TTS English voice cloning
WebAssembly speech enhancement
Detect spoken segments from your microphone in real time