OpenBMB/VoxCPM

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

Python36K stars4.1K forks+658 today

Topics

#audio#deeplearning#minicpm#python#pytorch#speech#speech-synthesis#text-to-speech#tts#tts-model#voice-cloning#multilingual#voice-design#voxcpm

What it does

VoxCPM2 is a tokenizer-free text-to-speech system that generates high-quality, multilingual speech with creative voice design and cloning capabilities. It matters because it offers unparalleled flexibility and quality in voice synthesis.

Star history

Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.

Tracking

Last trending: 2026-05-30

Creator kit

Hook

Transform text into lifelike speech across 30 languages with VoxCPM2's innovative TTS tech. Dive in now! 🎤💻

Content angles

Create a tutorial series showcasing how to use VoxCPM2 for multilingual voice cloning.
Analyze the impact of creative voice design on brand identity and customer engagement.
Compare VoxCPM2 with other popular text-to-speech solutions, highlighting its unique features and performance.

Who should care

AI researchers, developers working on speech synthesis, content creators looking for high-quality TTS solutions.