OpenBMB/VoxCPM

VoxCPMっていう音声生成AIの性能高すぎてバグってるよな。 これのおかげで、顔出し声出しナシでYouTube登録者1,800人突破した。 Xとかスレッズ×アフィは競合多いけど、動画×アフィやってる人少ないから、めっちゃブルーオーシャンでウハウハなのよね。 参考：VoxCPMで作った動画↓

Matched through a repo-specific project phrase query.

Trained a voice lora on Walken using just 6 clips as a test to see how well VoxCPM handles learning a voice. Then I just did audio + image = video with LTX 2.3. This TTS model feels extremely powerful, fully open sourced (Apache 2.0) More below 👇

Matched through a repo-specific project phrase query.

Trained another voice lora using VOXCPM. Also got the TTS running near real time with a Rust port and WSL Absolutely incredible. This one was trained on 20 clips. Not releasing these for obvious reasons - purely for science

Matched through a repo-specific project phrase query.

TTS presets are dead ☠️ The old way: pick a voice from a list and hope it sounds right. The new way: describe the voice you want in plain text. VoxCPM 2 generates it from scratch. 30+ languages. 48kHz. Open source. Zero reference audio. Here’s why this changes everything 👇

Matched through a repo-specific project phrase query.

🚀 VoxCPM 2 is trending on @HuggingFace ！ Tokenizer-Free #TTS for multilingual speech generation— now getting real traction 🎙️ Appreciate all the love from the community 🥰 🔗 Try it: huggingface.openbmb.com/mode… huggingface.co/spaces/openbm… #TTS #AI #OpenSource #OpenBMB

Matched through a repo-specific project phrase query.

I was paying for eleven labs so my @openclaw and @NousResearch agents would have a custom voice Until I found this free Voice cloner VoxCPM: github.com/OpenBMB/VoxCPM The audio quality and voice cloner is top tier! Check out my agent Makimas sexy voice 😌

Contains the canonical GitHub repository URL.

詳しくはこちら👇 github.com/OpenBMB/VoxCPM

Contains the canonical GitHub repository URL.

8. Try it here :) 🌐 Hugging Face Space: huggingface.co/spaces/openbm… 🤗 Hugging Face Model: huggingface.openbmb.com/mode… 🤖 ModelScope Model: modelscope.cn/models/OpenBMB… 💻 GitHub： github.com/OpenBMB/VoxCPM/

Contains the canonical GitHub repository URL.

1. VoxCPM 2 from OpenBMB. While other startups monetize voice AI, Chinese labs keep releasing it for free. This one uses Diffusion-Autoregressive Continuous Representation. Token-based approaches (Qwen3-TTS) lose acoustic metadata. This preserves emotional nuance at the continuous level.

Matched through a repo-specific project phrase query.