High-performance Coqui TTS API server with a hybrid "Hot/Cold" worker architecture
-
Updated
Apr 23, 2026 - Python
High-performance Coqui TTS API server with a hybrid "Hot/Cold" worker architecture
Local TTS plugin for Claude Code — 30 languages, voice design, voice cloning. Free, offline, powered by VoxCPM2.
One-click Pinokio installer for VoxCPM2 with voice cloning api and prompt memory.
High-throughput TTS server based on vLLM continuous batching. VoxCPM2 and future Transformer TTS models. Optimized for cloud deployment and multi-tenant serving.
A local-first TTS for twitch with VoxCPM2
Nano-vLLM optimized inference engine for VoxCPM2 TTS — torch.compile, FlashAttention, INT8, Triton kernels, CUDA Graph, OpenAI API
FastAPI TTS pool with Kokoro, VoxCPM2, and NanoVLLM-VoxCPM backends, a common synthesis API, queue scheduling, runtime model management, metrics, and GPU memory inspection.
OpenAI-compatible VoxCPM2 TTS adapter for zero-code Hermes integration via the speech API.
Turn PPTX speaker notes into narrated videos with AI voice cloning, subtitles, and translation.
Add a description, image, and links to the voxcpm2 topic page so that developers can more easily learn about it.
To associate your repository with the voxcpm2 topic, visit your repo's landing page and select "manage topics."