babelscribe
This server turns local audio/video files into subtitles and text using your own GPU, and helps you find media and inspect available devices, languages and models.
Transcribe any local media file to subtitles/text (
transcribe): give an absolute path to mp4, mkv, mov, mp3, wav, m4a, etc.Choose output formats:
srt,vtt,txt,json(segments with token timings) orasskaraoke word highlights, written next to the file or intooutput_dir.Pick the language: ISO code like
en,th,ja,es,hi, orautoto detect it.Go for accuracy with
accurate: true(large-v3 beam search, or the best fine-tune for Thai/Hindi).Fix spelling of names and jargon via the
vocabularyprompt (e.g. "Pitakpong, babelscribe").Translate the transcript to English with
translate: true.Find media files on the computer (
find_media): newest-first search of Downloads, Videos, Desktop, Music, Documents, filterable by folder and name.List GPUs whisper.cpp can use and which one is auto-selected (
list_devices).List available models and which model
--accurateuses per language (list_languages_and_models).
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@babelscribe Transcribe the newest video in my Downloads and save SRT subtitles"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
babelscribe — free, offline speech-to-text and subtitles on any GPU (AMD, NVIDIA, Intel, Apple)
babelscribe turns any audio or video file into subtitles (SRT, VTT) and text, in any of Whisper's 99 languages, on your own graphics card — AMD Radeon, NVIDIA, Intel Arc or Apple Silicon — or the CPU. No CUDA needed, no cloud, free (MIT). It runs OpenAI Whisper through whisper.cpp with Vulkan, CUDA or Metal, and works from the command line, from Python, or from AI apps (Claude, Codex, Antigravity, Gemini CLI, Cursor) as an MCP server.
pip install babelscribe # Python 3.9+
babelscribe interview.mp4 # auto-detects language, picks your best GPU -> interview.srt + interview.jsonbabelscribe is a thin, friendly layer on top of whisper.cpp. It exists because
getting fast Whisper on a non-NVIDIA card (e.g. an AMD Radeon on Windows) still means building whisper.cpp with the
Vulkan SDK yourself. babelscribe downloads a prebuilt whisper-cli for your system and handles the rest.
Your hardware | Backend used | Prebuilt asset |
AMD / NVIDIA / Intel GPU on Windows | Vulkan |
|
NVIDIA on Windows | Vulkan (same build) |
|
NVIDIA on Linux (alternative) | CUDA |
|
AMD / NVIDIA / Intel GPU on Linux | Vulkan |
|
Apple Silicon | Metal |
|
No usable GPU | CPU |
|
A 19-minute English TED talk transcribes in 48 seconds on an AMD Radeon RX 9070 XT with 1.5% word error — see the benchmark below.
Use it from an AI app (MCP) — no terminal needed
babelscribe is also an MCP server, so any AI app that supports local MCP servers can
transcribe files on your computer with your GPU. Ask in plain words — "make Thai subtitles for the newest video in
my Downloads" — and the app finds the file, transcribes it, writes .srt / .txt next to it, and can then proofread names,
translate or summarise the text for you.
Tools: transcribe (file → subtitles + text), transcribe_folder (every audio/video in a folder, one summary
back), find_media (newest audio/video in Downloads, Videos, Desktop, …), list_devices,
list_languages_and_models.
transcribe_folder goes on after a file fails and lists the failure in the summary. Subtitles land next to each
file, or under output_dir with the same sub-folders. Two files that would share a subtitle name (talk.mp4 and
talk.mp3) keep their full name: talk.mp4.srt, talk.mp3.srt.
Claude Desktop (one click): download babelscribe.mcpb from the latest release
and double-click it (or Settings → Extensions → Install extension).
Everything else runs the same command — uv fetches babelscribe for you:
uvx babelscribe mcp
App | How to add it |
Claude Code |
|
OpenAI Codex CLI |
|
Google Antigravity | agent panel → ⋯ → MCP Servers → Manage MCP Servers → View raw config, add the JSON below |
Gemini CLI | add the JSON below to |
Cursor | add the JSON below to |
VS Code (Copilot) |
|
{
"mcpServers": {
"babelscribe": { "command": "uvx", "args": ["babelscribe", "mcp"], "timeout": 3600000 }
}
}(timeout is in milliseconds and only some apps read it.) Already installed with pip? Use "command": "babelscribe", "args": ["mcp"].
Web-only chat apps (e.g. grok.com, chatgpt.com) can only reach servers on the internet, not your computer, so they can't use your GPU or files.
Related MCP server: video-transcriber-mcp
Benchmark: real talks, human captions as the answer key
Four TED / TEDx talks, scored against the human-made captions in the spoken language (bench/bench.py, reproducible).
Error = word error rate (WER) for space-separated languages, character error rate (CER) for Japanese and Thai.
GPU: AMD Radeon RX 9070 XT via Vulkan. default = large-v3-turbo; accurate = --accurate (see the FLEURS section).
Language | Talk | Length | default: time / error |
|
English | 19.3 min | 48 s (24x) · WER 1.5% | 107 s (11x) · WER 1.5% | |
Japanese | 16.2 min | 47 s (20x) · CER 4.7% | 115 s (8x) · CER 4.2% | |
Spanish | 19.9 min | 56 s (21x) · WER 13.8% | 134 s (9x) · WER 13.5% | |
Thai | นิติ ชัยชิตาทร — โปรดเรียกฉันด้วยนามอันแท้จริง (TEDxBangkok) | 14.1 min | 74 s (12x) · CER 22.7% | 565 s (2x) · CER 16.4% |
How to read it: TED captions are edited for reading (fillers dropped, light rewording), so these numbers are an upper bound —
most of the Spanish "errors" are the speaker's actual words versus the tidied caption. Thai is genuinely harder: fast,
casual speech with slang; --accurate (Pathumma Whisper text + turbo timing) cuts its error by more than a quarter.
Talks are used only to measure accuracy; their transcripts are not redistributed (TED content is CC BY-NC-ND).
Benchmark: 16 languages on FLEURS
Google FLEURS test set, 50 utterances per language, human-verified
verbatim transcripts (bench/fleurs.py, reproducible). Same normaliser for every language (Whisper's rule: lower-case,
drop punctuation and non-spacing marks, numbers spelled out). WER for space-separated languages, CER for ja / zh / ko / th.
Language | default (turbo) |
| model |
|
English | 6.1% | 5.7% | large-v3, beam 5 | 5.6% |
Spanish | 4.1% | 4.2% | large-v3, beam 5 | 2.6% |
French | 7.4% | 7.3% | large-v3, beam 5 | 7.2% |
German | 4.3% | 4.0% | large-v3, beam 5 | 3.3% |
Portuguese | 8.5% | 7.7% | large-v3, beam 5 | 5.3% |
Italian | 6.7% | 6.5% | large-v3, beam 5 | 3.8% |
Russian | 6.8% | 5.8% | large-v3, beam 5 | 5.6% |
Arabic | 11.0% | 10.6% | large-v3, beam 5 | 9.7% |
Hindi | 28.4% | 12.6% | vasista22/whisper-hindi-large-v2 + turbo timing | 11.1% |
Indonesian | 9.8% | 7.8% | large-v3, beam 5 | 5.6% |
Vietnamese | 10.8% | 9.1% | large-v3, beam 5 | 9.1% |
Turkish | 6.2% | 6.7% | large-v3, beam 5 | 5.8% |
Japanese (CER) | 6.4% | 5.7% | large-v3, beam 5 | 4.6% |
Chinese (CER) | 6.3% | 5.3% | large-v3, beam 5 | 4.8% |
Korean (CER) | 4.1% | 3.9% | large-v3, beam 5 | 3.1% |
Thai (CER) | 15.9% | 8.9% | Pathumma Whisper (NECTEC) + turbo timing | 8.8% |
* Some FLEURS clips contain more speech than their reference transcript, so a correct model is charged for words the
reference leaves out. Edge-trimmed ignores extra words before the first / after the last reference word; both numbers
are stored by bench/fleurs.py. 50 utterances per language means differences under ~0.5 points are noise.
Also measured and not used, because large-v3 was as good or better: large-v2 (all languages), PhoWhisper-large (vi 19.0%), whisper-large-v3 dialectal / code-switching Arabic fine-tunes (12.2% / 15.2%), Typhoon Whisper (th 11.9%), Thonburian Whisper (th 9.1% — kept as an option), Vaani Hindi (16.5%).
Why babelscribe (vs. what already exists)
GPU on AMD / Intel | Windows, no build step | Video in, subtitles out | Long files don't loop | Better text for your language | |
babelscribe | ✅ Vulkan | ✅ prebuilt | ✅ ffmpeg bundled | ✅ | ✅ hybrid fine-tune text + turbo timing |
whisper.cpp (raw) | ✅ Vulkan — if you compile it | ❌ official releases ship no Windows Vulkan build | ❌ WAV 16 kHz only | ⚠️ you must know the flag | ❌ |
faster-whisper / WhisperX | ❌ GPU = NVIDIA CUDA only | ✅ pip | ✅ | ⚠️ | ⚠️ manual |
Cloud APIs | n/a (cloud) | ✅ | ✅ | ✅ | ❌ — and your audio leaves your machine, paid per minute |
babelscribe does not replace those projects — it stands on whisper.cpp and simply removes the hard parts: compiling for your GPU, converting media, picking the right device, avoiding the long-file repeat bug, and combining a language-specific fine-tune with accurate timestamps.
FAQ
How do I run Whisper on an AMD GPU on Windows?
pip install babelscribe, then babelscribe video.mp4. It downloads a Vulkan build of whisper.cpp that runs on AMD Radeon
(and Intel Arc / NVIDIA) cards on Windows and Linux — no ROCm, no CUDA, no compiling.
How do I make subtitles (SRT) from a video for free, offline?
babelscribe video.mp4 -f srt writes video.srt next to the video. Nothing is uploaded; it runs on your own computer.
What is the most accurate free transcription for Thai?
babelscribe video.mp4 -l th --accurate — Pathumma Whisper (NECTEC) for the text plus Whisper turbo for timing:
CER 8.9% on Google FLEURS vs 15.9% for plain Whisper turbo. Thonburian Whisper is available too (--text-model thai-thonburian).
Can Claude / ChatGPT Codex / Gemini transcribe a video on my computer?
Yes — add babelscribe as an MCP server (see Use it from an AI app). Claude Desktop installs it with one click from
babelscribe.mcpb. The AI app can then find a file, transcribe it on your GPU, and proofread, translate or summarise the text.
How fast is it? About 20x real time with Whisper large-v3-turbo on an AMD Radeon RX 9070 XT: a 19-minute talk in 48 seconds.
Which languages are supported? All 99 Whisper languages, with automatic language detection. FLEURS error rates for 16 of them are in the benchmark table.
Is it better than faster-whisper or WhisperX? Those are excellent on NVIDIA GPUs; on AMD / Intel GPUs they fall back to the CPU. babelscribe's niche is any GPU, zero setup, and better Thai / Hindi through community fine-tunes. If you have an NVIDIA card and like Python, faster-whisper is a fine choice.
Languages
All 99 languages Whisper was trained on, auto-detected or forced with -l:
af am ar as az ba be bg bn bo br bs ca cs cy da de el en es et eu fa fi fo fr gl gu ha haw he hi hr ht hu hy id is it ja jw ka kk km kn ko la lb ln lo lt lv mg mi mk ml mn mr ms mt my ne nl nn no oc pa pl ps pt ro ru sa sd si sk sl sn so sq sr su sv sw ta te tg th tk tl tr tt uk ur uz vi yi yo yue zh
Accuracy follows Whisper's own training data: excellent for high-resource languages (English, Spanish, Japanese, …),
weaker for low-resource ones. That is what hybrid mode is for — a community fine-tune for one language can be plugged in
with one line in babelscribe/models.py (Thai and Hindi so far). PRs adding fine-tunes for other
languages are the most valuable contribution.
Limitations (honest)
Tested end to end so far on an AMD Radeon RX 9070 XT (Windows, Vulkan). CUDA, Linux and macOS builds are produced by CI; reports from those machines are welcome.
Hybrid mode runs two models, so it is slower (≈1 min per minute of audio with a large fine-tune on that GPU).
Proper nouns can still be misspelled — check names before publishing subtitles.
Features
Any input — mp4, mkv, mov, mp3, wav, m4a… (ffmpeg is bundled through
imageio-ffmpeg).Any language —
-l autodetects it; or pass-l th,-l ja,-l es…Picks the right GPU — prefers a discrete card over an integrated one;
babelscribe deviceslists them,--device Noverrides.Long files that don't loop — runs whisper with
--max-context 0, which stops the classic "same sentence repeated forever" hallucination on long recordings.Hybrid mode for better spelling in your language — community fine-tunes (e.g. Thai Thonburian Whisper) spell far better but often lose timestamps.
--text-modeltakes the text from the fine-tune and the timing fromlarge-v3-turbo, aligned character by character (works for languages without spaces), cut only at word boundaries, with the timing model filling any words the fine-tune skipped.--accurate— slower, fewest errors: large-v3 with beam search, or for Thai and Hindi the best community fine-tune (hybrid). Chosen per language from the FLEURS benchmark above.Custom vocabulary —
--prompt "Pitakpong, babelscribe"gives whisper an initial prompt that biases the spelling of names and jargon. In the MCPtranscribetool the same thing is thevocabularyargument. While a prompt is set,--max-context 0is not passed (whisper.cpp ignores the prompt otherwise).Translate to English —
--translatewrites the transcript translated to English (whisper's translate task, any source language). It useslarge-v3because turbo was not trained to translate, and cannot be combined with--text-model. In the MCPtranscribetool it is thetranslateargument.Outputs —
srt,vtt,txt,json(segments with token timings),ass(karaoke: each word highlights as it is spoken, from the token timings — for short-form video and players that read ASS).
Usage
babelscribe talk.mp4 -f srt,vtt,txt,json # all formats
babelscribe reel.mp4 -f ass # karaoke subtitles, one highlight per word
babelscribe podcast.mp3 -l en -m large-v3 # pick language and model
babelscribe talk.mp4 -l hi --accurate # slower, fewest errors (best model per language)
babelscribe vo.wav -l th --text-model thai-thonburian # hybrid: pick a Thai fine-tune yourself
babelscribe talk.mp4 --prompt "Pitakpong, babelscribe" # bias the spelling of names and terms
babelscribe talk.mp4 --translate # subtitles translated to English
babelscribe devices # GPUs whisper.cpp can see
babelscribe models # models and fine-tunes
babelscribe talk.mp4 --bin /path/to/whisper-cli # use your own whisper.cpp buildFrom Python:
from babelscribe.api import transcribe_file
r = transcribe_file("talk.mp4", lang="auto", formats=["srt", "txt"]) # or accurate=True, prompt="names, terms"
print(r["lang"], r["device"], r["files"]); print(r["text"][:200])Models download on first use to ~/.babelscribe/models (BABELSCRIBE_MODELS to change). Hybrid fine-tunes are converted on your
machine from their original Hugging Face repo — install pip install "babelscribe[finetune]" once; converted weights are never
redistributed, so each fine-tune keeps its own licence. Thai word boundaries: pip install "babelscribe[thai]".
Docker
No Python, ffmpeg or whisper.cpp on the host — the image has them, and the model is cached in a volume. There is no published image yet, so build it from a checkout, then run it on the folder that holds your media:
docker build -t babelscribe -f docker/Dockerfile .
docker run --rm -v "$PWD:/media" -v babelscribe-models:/models babelscribe talk.mp4 # writes talk.srt next to the inputCPU by default, linux/amd64; a Vulkan image for GPU hosts is one --build-arg away. Details: docker/README.md.
Roadmap
What's planned next (subtitle line wrapping, MCP progress for long files, folder batches, translate-to-English, more fine-tunes) is in ROADMAP.md and the open issues.
Add a language fine-tune
Add one entry to FINETUNES in babelscribe/models.py (Hugging Face repo, language code, whether it needs beam search) and open a PR.
Prebuilt binaries
.github/workflows/build-binaries.yml builds whisper-cli + whisper-quantize for every row of the table above and attaches
them to each v* release. Point BABELSCRIBE_RELEASES at another URL to self-host.
ภาษาไทย
ใช้ผ่าน Claude Desktop ได้โดยไม่ต้องพิมพ์คำสั่ง: โหลด babelscribe.mcpb จากหน้า Releases แล้วดับเบิลคลิก จากนั้นพิมพ์ในแชทว่า "ทำซับไทยให้คลิปล่าสุดในโฟลเดอร์ดาวน์โหลด"
ถอดเสียงจากไฟล์เสียงหรือวิดีโอได้ทุกภาษา บนการ์ดจอทุกยี่ห้อ (AMD / NVIDIA / Intel ผ่าน Vulkan, Apple ผ่าน Metal) หรือ CPU
ภาษาไทยแนะนำ babelscribe ไฟล์.mp4 -l th --accurate — ข้อความจาก Pathumma Whisper (NECTEC) ที่ผิดน้อยที่สุดใน FLEURS (CER 8.9% เทียบ turbo 15.9%) + เวลาจาก large-v3-turbo
หรือเลือก Thonburian Whisper เอง: --text-model thai-thonburian
Privacy Policy
babelscribe runs entirely on your own computer. Last updated 2026-10-06.
Data collection: none. babelscribe has no telemetry, analytics, accounts or crash reporting, and never uploads your audio, video, transcripts or file names anywhere.
What it processes and where: the media file you choose is converted and transcribed locally; subtitles and text are written to your disk (next to the file, or the folder you choose). Through MCP, the transcript text is returned to the AI app that called the tool — what that app does with it is governed by that app's own privacy policy.
Network access (downloads only): on first use it downloads the
whisper-cliprogram from this project's GitHub releases, speech models from Hugging Face (huggingface.co/ggerganov/whisper.cpp, and for--accurateThai/Hindi the fine-tune's own repository), and Python packages from PyPI when installed with pip/uv. These are plain downloads; no personal data is sent. GitHub, Hugging Face and PyPI see a normal download request (IP address, user agent) under their own privacy policies.Storage and retention: downloaded programs and models are cached in
~/.babelscribe(orBABELSCRIBE_HOME/BABELSCRIBE_MODELS) until you delete that folder. Outputs stay wherever they were written until you delete them. babelscribe keeps no other data.Third-party sharing: none.
Contact: open an issue at https://github.com/phonology024/babelscribe/issues
Credits & licence
MIT. Built on whisper.cpp (MIT) and OpenAI Whisper models (MIT). Fine-tunes belong to their authors: Pathumma Whisper by NECTEC, Thonburian Whisper by biodatlab, whisper-hindi-large-v2 by vasista22 (Speech Lab, IIT Madras).
Available Tools
4 toolsfind_mediaFind audio/video filesARead-only
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.
Inputs: limit, folder, name_contains. Returns: result
list_devicesList GPUsBRead-only
GPUs whisper.cpp can use on this computer and which one babelscribe picks automatically.
Inputs: no named parameters.
list_languages_and_modelsList languages and modelsCRead-only
Models available, and which model --accurate uses per language.
Inputs: no named parameters.
transcribeTranscribe audio/video to subtitlesAIdempotent
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.
Inputs: file_path (required), formats, accurate, language, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
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.
Maintenance
Related MCP Connectors
Transcribe audio and video and work with your transcript library from any AI app. 119 languages.
Transcribe audio and video files to text with timestamps and SRT or WebVTT subtitles
Transcribe, subtitle, dub and lip-sync media; create speech, voices, images and thumbnails.
Transcribes audio and video files to text, SRT, VTT and timestamped chunks for RAG.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables high-performance audio transcription using Faster Whisper with CUDA acceleration, supporting single and batch audio file processing with multiple output formats (VTT, SRT, JSON).-
- AlicenseNot gradedqualityBmaintenanceEnables high-performance, offline transcription of videos from 1000+ platforms and local files using whisper.cpp, with support for multiple model sizes, languages, and output formats over stdio or HTTP.20Apache 2.0
- AlicenseAqualityDmaintenanceEnables MCP clients to transcribe audio/video files locally, generate SRT subtitles, and burn captions into videos via tool calls, without a cloud API.3MIT
- AlicenseNot gradedqualityBmaintenanceProvides local, offline transcription, keyframe extraction, OCR, and pre-publish review of audio, video, and image files, enabling AI agents to see and hear media without cloud or API keys.55 npmApache 2.0