boson-ai/higgs-audio

open source audio model for expressive speech and voice cloning

open-source model for speech-to-speech and audio understanding
stepfun-ai/Step-Audio2
speech-to-speech pipeline using open models for voice detection, transcription, language modeling, and speech synthesis
huggingface/speech-to-speech
open-weight text-to-speech model for fast, natural voice synthesis
hexgrad/kokoro
Speech-to-text model for audio transcription, translation, and language detection
openai/whisper
open source speech recognition toolkit with ASR, VAD, speaker verification, and model zoo
modelscope/FunASR
audio foundation model for understanding, generation, and conversation
MoonshotAI/Kimi-Audio
open source text-to-speech model with voice cloning and emotion control
resemble-ai/chatterbox
Text-to-audio model that generates speech and sounds from text
suno-ai/bark
speech interface tools for audio comprehension and generation
stepfun-ai/Step-Audio
toolkit for audio, music, and speech generation research
open-mmlab/Amphion