Discover the best open-source text-to-speech, speech-to-text, voice cloning, voice activity detection and LLM models you can self-host — each with its GitHub stars, license and a link to the repo.
Submit an open-source productFireRedTeam — FireRedTTS2 is FireRedTeam's open-source text-to-speech model for natural, expressive voice generation.
SpeechBrain — A PyTorch-based Speech Toolkit
Speechmatics — Open-source AI speech tech for enterprise, offering real-time transcription, translation, and TTS.
DeepSeek-V3 — DeepSeek-V3 — open source.
Kyutai — Moshi is a speech-text foundation model and full-duplex spoken-dialogue framework, using Mimi, a state-of-the-art streaming neural audio codec — enabling real-time, natural voice conversation.
LuxTTS — LuxTTS is an open-source text-to-speech model.
FluidVoice — FluidVoice is an open-source voice dictation / speech-to-text tool.
Kyutai — Hibiki is a model for streaming (simultaneous) speech translation — it adapts in real time to produce a correct translation chunk by chunk, rather than waiting for the full utterance.
ESPnet — End-to-End Speech Processing Toolkit
Ultravox — Real-time, speech native voice AI infrastructure for fast, natural, scalable voice agents.
QwenLM — Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.
DeepSpeech — DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
Myshell — High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.
Silero VAD — Silero VAD: pre-trained enterprise-grade Voice Activity Detector
Kyutai — Kyutai's open speech-to-text and text-to-speech models built on the Delayed Streams Modeling framework for streaming, low-latency speech.
QwenLM — Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.
Moonshot AI — MoBA: Mixture of Block Attention for Long-Context LLMs
NVIDIA NeMo — A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)