App for translating text or voice input from various sources into text or voice output
1.5K
The anytran project is a sophisticated real-time audio translation tool with:
• 3-stage pipeline: Speech-to-text → Text Translation → Text-to-Speech
• Multiple input sources: Files, RTSP, YouTube, system output, web browser
• Modular architecture: Separate runners for each input type, pluggable backends
• Comprehensive CLI: 50+ options for fine-grained control
This docker image matches the github repo here: https://github.com/otherroch/anytran
This simple docker command can be used to run it:
docker run -it --gpus all otherroch/anytran --help
Content type
Image
Digest
sha256:9e4dcd8b1…
Size
1.4 GB
Last updated
3 months ago
docker pull otherroch/anytran:latest-bookworm-arm64