babelscribe
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BABELSCRIBE_HOME | No | Change the cache directory where downloaded programs and models are stored (default is ~/.babelscribe). | |
| BABELSCRIBE_MODELS | No | Change the directory where speech models are downloaded (default is ~/.babelscribe/models). | |
| BABELSCRIBE_RELEASES | No | Point at another URL to self-host the prebuilt whisper-cli binaries instead of using this project's GitHub releases. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Local speech-to-text on the user's own GPU (AMD/NVIDIA/Intel/Apple) for 99 languages. Needs a file path on this computer: if the user only names or describes a file, call find_media first. Subtitles (.srt) and text (.txt) are written next to the media file unless output_dir is given. Use accurate=true when the user wants the fewest mistakes (slower); it is much better for Thai and Hindi. The first run downloads the model (~1.6 GB), so it can take a few minutes. After transcribing you can proofread names, translate, or summarise from the returned text.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| transcribeA | Transcribe a local audio or video file into subtitles / text. file_path: absolute path to the media file (mp4, mkv, mov, mp3, wav, m4a, ...). language: ISO code such as en, th, ja, es, hi — or "auto" to detect. accurate: slower, fewest errors (large-v3 with beam search, or the best fine-tune for Thai / Hindi). formats: comma list from srt, vtt, txt, json, ass (ass = karaoke word highlight). output_dir: folder for the output files; empty = next to the media file. vocabulary: names and terms to spell correctly, e.g. "Pitakpong, babelscribe" (whisper initial prompt); empty = none. translate: true = write the transcript translated to English (uses large-v3; slower than turbo). Returns the files written, detected language, device used, and the transcript text. |
| find_mediaA | Find audio/video files on this computer, newest first. Searches Downloads, Videos, Desktop, Music and Documents (two levels deep) unless folder is given. Use it when the user names a file without a full path. |
| list_devicesB | GPUs whisper.cpp can use on this computer and which one babelscribe picks automatically. |
| list_languages_and_modelsC | Models available, and which model --accurate uses per language. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct role: transcribe performs the core action, find_media resolves paths, list_devices reports GPU availability, and list_languages_and_models reports model/language info. The two list_* tools are separated by resource (devices vs. models/languages), so there's no realistic confusion.
Three tools follow a snake_case verb_noun pattern (find_media, list_devices, list_languages_and_models) while the core action is a bare verb (transcribe). This is a minor, readable deviation rather than a convention clash.
Four tools for a focused transcription server is well-scoped: one action tool plus three small discovery/introspection helpers. Nothing feels redundant, and each tool earns its place.
The core workflow is well covered — file discovery, device selection, model/language lookup, and transcription with formats, translation, and vocabulary hints. Gaps remain for job progress/status on long files and batch transcription of multiple media files, which agents can only work around by calling transcribe repeatedly.