voxcpm

GitHub

Tokenizer-free Text-to-Speech (TTS) model for multilingual speech generation, voice design, and cloning.

First seen: Apr 9, 2026

Visit website

AI Summary

Tokenizer-free Text-to-Speech (TTS) model for multilingual speech generation, voice design, and cloning.

Best for

Multilingual speech generation / Creative voice design / Voice cloning

Why it matters

VoxCPM2 offers a tokenizer-free approach to TTS, enabling more natural and flexible speech synthesis across multiple languages and allowing for the creation of custom voices.

Key Features

Tokenizer-free TTS architecture
Multilingual speech synthesis
Creative voice design capabilities
True-to-life voice cloning

Use Cases

Generating speech in various languages
Developing unique synthetic voices
Replicating specific voice characteristics
Content creation requiring diverse audio outputs

Why Now

VoxCPM2, a tokenizer-free TTS model for multilingual speech generation and voice cloning, has recently emerged on GitHub, suggesting early-stage development and potential for innovation in creative voice design.

Community Signals

Trend score

2.5

24h momentum

Rising

Facts / Signals / Inference / Unknowns

Facts

Listed on GitHub as "voxcpm".
Source description: Star OpenBMB / VoxCPM VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning.
Description: Star OpenBMB / VoxCPM VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning.
GitHub repository is linked as openbmb/voxcpm.
Primary public product URL is https://github.com/openbmb/voxcpm.

Signals

GitHub mention is recent (2026-04-09).
GitHub itself is already one of the observed discovery sources.
Primary discovery source is GitHub.

Inference

Public code access can lower evaluation friction for developer audiences.

Unknowns

Documentation is not explicitly linked in the current allowed evidence set.
No tagline is stored on the current product record.
Pricing details are not explicitly linked in the current allowed evidence set.
Recent changelog or release history is not explicitly linked in the current allowed evidence set.
Release cadence cannot be confirmed unless a changelog or release link is explicitly provided.