VoxCPM2 Technical Report
π Attachment: VoxCPM2 Technical Report 2606.06928v1.pdf
Developer Showcase
View all βESP32 Radar Tower: AI ATC CalloutsA round-AMOLED tower radar announcing flights in a cloned ATC voiceVoxWeft: On-Device Interpretation on MacVoxCPM2 ported to MLX for fully local streaming speech-to-speech interpretationKahya TTS: Turkish Voice CloningTurkish TTS fine-tuned from VoxCPM2 with reference-based voice cloningVoiceMem: Streaming Dual-Brain Voice MemoryA streaming dual-brain memory giving voice agents low-latency, emotional memoryYouDub: Open-Source Video LocalizationTranscribe, translate and dub videos with sentence-level voice cloningCoreAI Model Zoo: MiniCPM on iPhoneCore AI builds of MiniCPM5 and MiniCPM-V 4.6 running natively on iPhone and Macbaby mynah: Morphing Between 9 AccentsVoxCPM-0.5B with one LoRA per accent, blended in weight spaceTalk to Fengge: A Real-Time Voice ClonePhone-style voice chat with an AI clone that captures both voice and personaWhispera: Local Real-Time Voice ChatFully local voice chat on Windows with barge-in, SenseVoice ASR and VoxCPM streaming TTSNekoAudio-80K: a 300 GB Open Catgirl Audio DatasetGive your catgirl a voice: time to train some TTS!VoxCPM CLI: Local TTS via OpenVINOA JSON-first, PyTorch-free VoxCPM2 CLI on OpenVINO, shipped with an agent Skill