Open Source Models for Voice AI

Moonshot AI — Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

ChatTTS — A generative speech model for daily dialogue.

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

Speechmatics — Open-source AI speech tech for enterprise, offering real-time transcription, translation, and TTS.

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)

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

Dograh — Open-source voice platform for custom, self-hosted voice agents and pipelines.

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

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

LuxTTS — LuxTTS is an open-source text-to-speech model.

KugelAudio — Europe's first production-ready TTS with 40+ languages, developed and hosted in Europe, fully GDPR compliant.

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

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

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

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

Silero VAD — Silero VAD: pre-trained enterprise-grade Voice Activity Detector

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.

Bolna AI — Voice AI built for India

pyannote.audio — Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Llama — Inference code for Llama models

QwenLM — Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.

LobbyStack — Open-source AI receptionist that answers calls, qualifies leads, books appointments, and routes urgent requests 24/7.

Whisper — Robust Speech Recognition via Large-Scale Weak Supervision

ESPnet — End-to-End Speech Processing Toolkit

Julius — Open-Source Large Vocabulary Continuous Speech Recognition Engine

GLM-5 — GLM-5: From Vibe Coding to Agentic Engineering

Coqui TTS — 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

F5-TTS — Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

OpenHome — OpenHome — open-source OS for AI voice agents, LLM-agnostic and ship-ready for real hardware.

FireRedTeam — FireRedTTS2 is FireRedTeam's open-source text-to-speech model for natural, expressive voice generation.