11
WebAssembly English TTS (sherpa-onnx)
π»
Generate speech from text with adjustable speed
FSA/FST algorithms, differentiable, with PyTorch compatibility. Automatic speech recognition
Generate speech from text with adjustable speed
Detect voice in spoken audio recordings
Recognize and transcribe spoken Japanese
Convert spoken words to text with voice input
Turn speech into text using Kaldi with VAD + ASR
Recognize speech and detect voice activity
Transcribe spoken words into text in real-time
Transcribe audio to text in multiple languages
Convert spoken Thai to text using voice input
Transcribe spoken Chinese into text
Convert spoken words into text
WebAssembly + Moonshine + VAD for ASR
Speaker diarization with Next-gen Kaldi and WebAssembly
Generate speech from text using Kaldi and WebAssembly