🐙 GitHub Detail
hwdsl2/docker-kokoro
By hwdsl2
Docker image to run a self-hosted Kokoro TTS server with an OpenAI-compatible audio speech API. 50+ voices across 9 languages, streaming support, all major audio formats, NVIDIA GPU (CUDA) acceleration, offline mode, and persistent model cache. Multi-arch: amd64, arm64.
Live Snapshot
⭐
Stars
16
🍴
Forks
2
📄
License
Other
🧩
Type
Python
About this open-source project
Live information fetched from GitHub.
Docker image to run a self-hosted Kokoro TTS server with an OpenAI-compatible audio speech API. 50+ voices across 9 languages, streaming support, all major audio formats, NVIDIA GPU (CUDA) acceleration, offline mode, and persistent model cache. Multi-arch: amd64, arm64.
Default Branch
main
Open Issues
0
Watchers
16