io.github.phonology024/babelscribe
babelscribe
Offline speech-to-text and SRT subtitles in 99 languages on your own AMD/NVIDIA/Intel/Apple GPU.
alive probed 2026-10-15
4tools
790tokens in Claude Opus 5.5
830tokens in Claude Code
0.4 %of a 200k context window
455o200k_base estimate
3.0 sto initialize
6 msto list tools
- Run it
- uvx babelscribe==0.3.2 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- babelscribe 0.3.2
- Capabilities
- prompts, resources, tools
- Instructions
- 557 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-15. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/phonology024/babelscribe
- Website
- https://phonology024.github.io/babelscribe/
- Registry
- active, updated 2026-10-06 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| transcribe | 259 | 57 % |
| find_media | 112 | 25 % |
| list_devices | 42 | 9 % |
| list_languages_and_models | 42 | 9 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.phonology024/babelscribe)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.