VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
Talk to 峰哥 — 克隆任何人的声音和性格，实时语音对话，工程延迟 < 1 秒 | Clone anyone's voice & personality for real-time conversation. < 1s engineering latency.
TTS-Story is a web-based multi‑voice TTS studio for turning tagged scripts into audiobooks—featuring full speaker management, chunk review/regeneration, a job queue and library system, and local GPU or API backends including Kokoro, Chatterbox, VOX CPM, Pocket-TTS, Kitten-TTS, IndexTTS-2, QWEN3 TTS and Omnivoice engines
A clean, efficient ComfyUI custom node for VoxCPM TTS (Text-to-Speech) functionality. This implementation provides high-quality speech generation and voice cloning capabilities using the VoxCPM 1.5 model.
DubCue is a local AI dubbing director for script-based voiceover workflows, currently built around VoxCPM2 with multi-model local TTS support in development.
Build voice apps fast. Unified API for speech recognition & synthesis with streaming, WebSocket, and multi-engine support.
One-click Pinokio installer for VoxCPM2 with voice cloning api and prompt memory.
Standalone C++ inference project for VoxCPM models built on top of ggml with API Frontend
Multi-engine TTS server (Qwen3-TTS + VoxCPM2): MLX & PyTorch backends, voice cloning, incremental PCM streaming, one-model-in-VRAM manager with idle eviction.
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.
Local VoxCPM2 text-to-speech API server for Apple Silicon (MLX) — voice design + voice cloning, OpenAI-style endpoint
VoiceGen Oui!: Windows + WSL2 bridge for ROCm-powered VoxCPM2 voice generation on AMD GPUs. RX 7900 XTX verified; AMD GPU testers welcome.
Generate high quality synthetic TTS training audio from text datasets
Production-ready multi-agent framework with VoxCPM orchestration, Ollama local LLMs, and Streamlit UI.
Voice cloning software for multi-person dialogue synthesis.
Reverse-Turing webcam interrogation game. An AI interrogator (A.M.N.) uses webcam, microphone, pulse detection, and micro-expression analysis to determine if you're human.
Add a description, image, and links to the voxcpm topic page so that developers can more easily learn about it.
To associate your repository with the voxcpm topic, visit your repo's landing page and select "manage topics."