SOTA Open Source TTS
Open speech-to-speech models and pipelines by Hugging Face toolkit AI
Speech-AI-Forge is a project developed around TTS generation model
Robust Speech Recognition via Large-Scale Weak Supervision
Buzz transcribes and translates audio offline
Multilingual speech recognition and audio understanding model
TTS with kokoro and onnx runtime
A TTS that fits in your CPU (and pocket)
Industrial-level controllable zero-shot text-to-speech system
Faster Whisper transcription with CTranslate2
High-Quality Voice Cloning TTS for 600+ Languages
Open Source Speech Language Model
VoiceStudio is the open-source, fully-local ElevenLabs alternative
Tokenizer-Free TTS for Multilingual Speech Generation
Translate the video from one language to another and embed dubbing
Qwen3-TTS is an open-source series of TTS models
Use Microsoft Edge's online text-to-speech service from Python
Open-source framework for intelligent speech interaction
Automatic Speech Recognition with Word-level Timestamps
Speech recognition module for Python
Offline Text To Speech synthesis for python
Comprehensive Gradio WebUI for audio processing
PersonaPlex code
State-of-the-art TTS model under 25MB
StreamSpeech is a seamless model for offline speech recognition