OSI-openOpen voice and text-to-speech

VoxCPM

OpenBMB

Tokenizer-free TTS from OpenBMB covering 30 languages with voice design and real-time streaming.

26.1k stars(as of 2026-06-05)View on GitHub

Overview

What is VoxCPM?

A tokenizer-free TTS system from OpenBMB. VoxCPM2 (2B parameters) covers 30 languages including German, supports voice design from a text description (no reference audio), and streams in real time.

Analysis

Pros & Cons

Pros

Apache-2.0 including the weights - genuinely free to use commercially
30 languages with voice design and cloning
Dedicated inference engines with an OpenAI-compatible audio endpoint

Cons

Needs a GPU (~8 GB VRAM, CUDA 12+); Linux is the primary target
The README itself notes voice-design results vary between runs
Real-time factor depends heavily on hardware

License

Apache-2.0 (OSI-open)

When it is interesting

Self-hosters with a GPU who want true commercial freedom.

When it is too early

CPU-only setups or anyone who needs a managed API.

This repo featured in the 2026-06 edition of the Open-Source AI Radar.

Similar repositories

voicebox

jamiepine

29.5k

A free, on-device alternative to ElevenLabs for TTS, voice cloning and dictation.

OSI-openOpen voice and text-to-speech

Chatterbox

resemble-ai

25.1k

MIT-licensed open TTS with zero-shot voice cloning - 500M params, 23+ languages.

OSI-openOpen voice and text-to-speech

supertonic

supertone-inc

11.3k

Fast on-device TTS via ONNX with 31-language support, running on CPU, browser and mobile.

Open weight, with conditionsOpen voice and text-to-speech