kyutai-labs/moshi

real-time speech-to-speech AI model for natural conversations

Lets text models hear you and talk back using speech-to-text and text-to-speech
kyutai-labs/unmute
open-weight text-to-speech model for fast, natural voice synthesis
hexgrad/kokoro
AI model for zero-shot speech editing and text-to-speech
jasonppy/VoiceCraft
open-source model for speech-to-speech and audio understanding
stepfun-ai/Step-Audio2
Voice AI repo for context-aware audio conversation models
fluxions-ai/vui
AI tool for local interview transcription with speaker detection, no cloud needed
kaixxx/noScribe
Ultravox: open-source model that handles both text and voice inputs for conversational AI
fixie-ai/ultravox
Text-to-dialogue model, clones voices
nari-labs/dia
speech-to-speech pipeline using open models for voice detection, transcription, language modeling, and speech synthesis
huggingface/speech-to-speech
AI-powered audio processing tool with speech recognition, translation, and TTS
abus-aikorea/voice-pro