#speech

huggingface/speech-to-speech

Build local voice agents with open-source models

huggingface/speech-to-speech

Build local voice agents with open-source models

The Alice and Bob After Dinner Speech (1984)

moonshine-ai/moonshine

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

handy-computer/transcribe.cpp

ggml speech-to-text inference for 16+ model families

Show HN: Orate – On-device neural text-to-speech queue for Mac

Time-Frequency Consistency Learning for Robust Speech Deepfake Detection

EEG shows brain can simultaneous encode two speech streams

Speech Recognition and TTS in less than 500kb

Mexico Speech Laws for Protecting the Powerless Instead Used to Silence Critics

Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro

Silent speech with ultrasound

Speech and Noise Corpora for Pitch Estimation of Human Speech