The Free, Open-Source Alternative to ElevenLabs Is Finally Here

30 languages, 48kHz output, context-aware prosody. Design any voice from text. Clone from a short clip with style guidance. No language tags. Everything runs locally. Free for commercial use.

Bytefer

Follow

4 min read

·

May 5, 2026

475

1

Listen

Share

Press enter or click to view image in full size

I have already introduced several excellent TTS models, including Qwen3-TTS, Fish Audio S2 Pro, and Voxtral TTS. Recently, the OpenBMB team released the latest VoxCPM2 model, which has 2B parameters, supports voice cloning, voice design, and high-quality speech synthesis, and supports 30 mainstream languages, including English, Chinese, Japanese, Korean, German, and French.

VoxCPM2 Features

• Supports 30 languages, no language tags required, direct input of text in any supported language.
• Supports voice design, input natural language descriptions to generate new voices without reference audio.
• Supports voice cloning, with style guidance to control emotion, pace, and expressiveness.
• Supports generating high-quality 48kHz audio.

VoxCPM Architecture

VoxCPM adopts a tokenizer-free, diffusion autoregressive architecture that…