Open Source Models for Voice AI

Kyutai — Pocket TTS is a compact text-to-speech model small enough to run on a CPU — fast, lightweight, on-device voice generation.

neutts — On-device TTS model by Neuphonic

Real-Time Voice Cloning — Clone a voice in 5 seconds to generate arbitrary speech in real-time

Bolna AI — Voice AI built for India

Whisper — Robust Speech Recognition via Large-Scale Weak Supervision

Llama — Inference code for Llama models

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

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)

SpeechBrain — A PyTorch-based Speech Toolkit

CosyVoice — Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Resemble AI — SoTA open-source TTS

FluidVoice — FluidVoice is an open-source voice dictation / speech-to-text tool.

VibeVoice — Open-Source Frontier Voice AI

Vosk — Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

Hume AI — TADA is an open-source speech-language model from Hume AI.

Agora — Real-time voice AI platform enabling natural, low-latency conversations.

Kyutai — Kyutai's open speech-to-text and text-to-speech models built on the Delayed Streams Modeling framework for streaming, low-latency speech.

FireRedTeam — FireRedASR is FireRedTeam's open-source automatic speech recognition (ASR) model for high-accuracy speech-to-text.

ESPnet — End-to-End Speech Processing Toolkit

MiniMax — MiniMax-M3 is an open-source large language model released by MiniMax, available on GitHub to run and build on.

Voicebox — Open Source Voice Cloning Desktop App for Mac, Windows, and Linux.

Izwi — Voice AI runtime for private deployment with an OpenAI-compatible API.

Rapida — Open-source Voice AI platform for contact centers, enterprises, and agencies with full deployment control.

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.

TEN Framework — Voice Activity Detector (VAD) : low-latency, high-performance and lightweight

Fish Audio — Open-source AI voice platform with high-quality TTS and voice cloning in multiple languages.

FireRedTeam — FireRedChat is FireRedTeam's open-source real-time, full-duplex conversational voice agent.

Gemma — Gemma open-weight LLM library, from Google DeepMind

Rasa — The developer platform for enterprise AI agents.

VoiceMesh — A production-inspired reliability lab for real-time voice AI infrastructure — full VAD to STT to LLM to TTS pipeline with observability, event streaming, durable workflows, and billing.