Open Source Models for Voice AI

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

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

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

Julius — Open-Source Large Vocabulary Continuous Speech Recognition Engine

Bolna AI — Voice AI built for India

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

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

Dia2-2B — Dia2-2B by nari-labs — open-source model on Hugging Face.

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

Gradium — Build expressive, low latency voice AI with a unified API for text, speech, and cloning.