VoxCPM
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
- 43k
- Python
- Apache-2.0
- 13 d ago
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
Open-source AI video localization and dubbing for YouTube/Bilibili: speech recognition, subtitle translation, voice cloning, audio mixing and rendering. 开源 AI 视频翻译配音工具。
Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read text in 30 languages. Patched audio.cpp, local UI in 30 languages, 14 ready-made voices.
Ahenk: açık Türkçe metinden sese. Open Turkish text-to-speech: VoxCPM2 LoRA (Ahenk), 8.6M on-device model (Ahenk Cep), trnorm text normaliser, TR-Zor benchmark
Offline AI narration studio for Android: turn scripts into natural speech and clone your voice, all on-device. No cloud, no account.
Open text-to-speech engines on one platform: CosyVoice, F5-TTS, GPT-SoVITS, OmniVoice, Qwen3-TTS, VoxCPM, Fish Speech and IndexTTS. They share one web UI, one command line and one HTTP API. Speak, clone and design voices, convert and edit speech, read whole books with a cast of voices, and fine-tune models on your own recordings.
No longer developed. Use Speech Studio: https://github.com/timoncool/speech-studio. One-click Pinokio launcher for VoxCPM2 Portable. Multilingual TTS (30 languages), Voice Design, Voice Cloning, end-to-end LoRA fine-tuning. Cross-platform (Win/Linux/macOS, NVIDIA/AMD/CPU).
⚡ A talking desktop Pikachu that runs 100% on-device — MiniCPM5-1B brain + VoxCPM voice + Nemotron ears, every model ≤1B params. No cloud, works with the Wi-Fi off.
19 speech engines + Whisper: Kokoro, XTTS v2, F5-TTS, Chatterbox, Fish Speech, Bark, Dia, Higgs Audio, Qwen Omni, VibeVoice, SpeechT5, Parler, OuteTTS, VITS, Edge, Voxtral, VoxCPM2, CSM and Orpheus. Voice cloning, SRT, audio editor, CLI/API. Offline Kokoro included. From portable-linux-in-a-box.