Run any Skill in Manus with one click

transcribe-video

Stars32

Forks0

UpdatedJune 2, 2026 at 19:05

Use when the user wants to transcribe a video or audio file to text with word-level timestamps — spins up a self-contained local Whisper (whisper.cpp) Docker service bundled in this skill and returns transcript.txt, transcript.srt, and word-level transcript.words.json. Also used as a building block by /produce-video. Triggers on "transcribe this video", "get a transcript", "transcribe-video".

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

AlemTuzlak

AlemTuzlak/skills

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

12 files

SKILL.md

readonly

name	transcribe-video
description	Use when the user wants to transcribe a video or audio file to text with word-level timestamps — spins up a self-contained local Whisper (whisper.cpp) Docker service bundled in this skill and returns transcript.txt, transcript.srt, and word-level transcript.words.json. Also used as a building block by /produce-video. Triggers on "transcribe this video", "get a transcript", "transcribe-video".

Transcribe Video

Transcribes any video/audio file locally using a bundled whisper.cpp service. No external project or cloud API. Returns word-level timestamps (needed for synced overlays/captions).

When to use

"Transcribe this clip / video / audio", "get me a transcript with timestamps".
As a sub-step of /produce-video.

How it runs

Everything is driven by the bundled runner — never ask the user to manage Docker:

node scripts/transcribe.mjs <path-to-video-or-audio> [--out <dir>] [--port 9111] [--language en] [--no-word-ts] [--task transcribe|translate]
node scripts/transcribe.mjs --stop      # stop the warm container

The runner:

Checks the Docker daemon is reachable (fails loud with guidance if not).
Builds the transcribe-video-whisper image from assets/whisper-service/ if it is missing (first build is slow: it compiles whisper.cpp and bakes the ggml-base.en.bin model).
Starts the transcribe-video-whisper container (host port 9111 → container 9001); reuses it if already running, docker starts it if stopped.
Waits for GET /healthz to report ok.
Extracts a 16 kHz mono WAV from the input with local ffmpeg (whisper.cpp only decodes WAV), then POSTs it to /transcribe with word_ts=true.
Writes transcript.txt, transcript.srt, transcript.words.json to --out (default: the input file's directory), and prints a JSON result line to stdout.

Outputs

transcript.txt — plain text.
transcript.srt — subtitle text.
transcript.words.json — [{ "word", "start", "end" }], seconds, time-ordered. This is the sync source for overlays/captions.

stdout result line (for programmatic callers like /produce-video):

{ "ok": true, "outDir": "...", "wordCount": 38, "segmentCount": 2, "files": { "txt": "transcript.txt", "srt": "transcript.srt", "words": "transcript.words.json" } }

Requirements

Docker is REQUIRED — the Whisper service runs in a container, so Docker Desktop must be installed AND running. The runner checks this first and fails loud with install/start guidance if Docker is missing or its daemon is down; there is no non-Docker fallback.
ffmpeg is REQUIRED (used to extract a 16 kHz mono WAV for Whisper) — the runner checks for it up front and fails loud if it is not on PATH.
Node ≥ 22.

Notes

The container is left running (--restart unless-stopped) for warm reuse; stop with --stop.
If word timestamps are requested but none come back, the runner fails loud (overlay sync depends on them).
See references/ for the Docker lifecycle, the API shape, and the vendoring provenance.

More from this repository

same repository

docs

AlemTuzlak/skills

Use when writing, editing, or organizing documentation, when planning what docs a feature needs, and whenever planning or implementing a new feature or change in a repo (docs ship with the code). Triggers on "write docs for X", "document this feature", "add a guide", "update the docs", "reorganize the docs", "plan feature X", "implement X", or /docs.

2026-07-1632

rfc

AlemTuzlak/skills

Use when the user wants to write, draft, or author an RFC (Request for Comments) / technical design doc for a feature, change, or architectural decision. Interactively interviews the user, grounds the proposal in the actual codebase, presents 2-3 concrete API/code-snippet approaches to choose from, then writes a review-ready RFC. Triggers on "write an RFC", "draft an RFC", "RFC for X", "design doc for X", or /rfc.

2026-07-1632

presentation

AlemTuzlak/skills

Use when the user wants to create presentation slides, a slide deck, a technical talk, or a conference talk for a topic or library — built on Slidev. Interviews the user, deep-researches and code-grounds the topic FIRST, applies presentation-craft best practices, generates a Slidev deck, self-verifies it in a headless browser, and ends with the dev server running and the deck open in the browser with zero manual steps. Triggers on "make a presentation", "make slides", "build a deck", "presentation about X", "technical talk", "conference talk", "slidev deck", "build slides for X", "present <library>".

2026-06-0732

hyperframes-video

AlemTuzlak/skills

Use when the user wants to generate a rendered promotional video (not just a script) for a PR, feature, or product change — produces a HyperFrames HTML composition, iterates with `npx hyperframes preview`, and outputs mp4 + poster for X/LinkedIn/social.

2026-06-0432

produce-video

AlemTuzlak/skills

Use when the user wants to turn a raw talking-head / screen-share recording into a finished, edited, annotated video plus a full content package. Removes silences, flags mistakes for the user to cut, transcribes, adds transcript-synced overlays (code, on-screen code highlights, word highlights, lists, comparisons, diagrams, section labels, punch-in zooms), renders with original audio, then generates blog/socials/YouTube content. Triggers on "produce a video", "edit my video", "annotate my recording", "/produce-video".

2026-06-0232

blog-post

AlemTuzlak/skills

Use when the user wants to write a blog post about a feature, product change, PR, git diff, or any technical topic - accepts marketing briefs, PRs, git refs, codebase paths, or freeform descriptions as input

2026-06-0232

name	transcribe-video
description	Use when the user wants to transcribe a video or audio file to text with word-level timestamps — spins up a self-contained local Whisper (whisper.cpp) Docker service bundled in this skill and returns transcript.txt, transcript.srt, and word-level transcript.words.json. Also used as a building block by /produce-video. Triggers on "transcribe this video", "get a transcript", "transcribe-video".

Transcribe Video

Transcribes any video/audio file locally using a bundled whisper.cpp service. No external project or cloud API. Returns word-level timestamps (needed for synced overlays/captions).

When to use

"Transcribe this clip / video / audio", "get me a transcript with timestamps".
As a sub-step of /produce-video.

How it runs

Everything is driven by the bundled runner — never ask the user to manage Docker:

node scripts/transcribe.mjs <path-to-video-or-audio> [--out <dir>] [--port 9111] [--language en] [--no-word-ts] [--task transcribe|translate]
node scripts/transcribe.mjs --stop      # stop the warm container

The runner:

Checks the Docker daemon is reachable (fails loud with guidance if not).
Builds the transcribe-video-whisper image from assets/whisper-service/ if it is missing (first build is slow: it compiles whisper.cpp and bakes the ggml-base.en.bin model).
Starts the transcribe-video-whisper container (host port 9111 → container 9001); reuses it if already running, docker starts it if stopped.
Waits for GET /healthz to report ok.
Extracts a 16 kHz mono WAV from the input with local ffmpeg (whisper.cpp only decodes WAV), then POSTs it to /transcribe with word_ts=true.
Writes transcript.txt, transcript.srt, transcript.words.json to --out (default: the input file's directory), and prints a JSON result line to stdout.

Outputs

transcript.txt — plain text.
transcript.srt — subtitle text.
transcript.words.json — [{ "word", "start", "end" }], seconds, time-ordered. This is the sync source for overlays/captions.

stdout result line (for programmatic callers like /produce-video):

{ "ok": true, "outDir": "...", "wordCount": 38, "segmentCount": 2, "files": { "txt": "transcript.txt", "srt": "transcript.srt", "words": "transcript.words.json" } }

Requirements

Docker is REQUIRED — the Whisper service runs in a container, so Docker Desktop must be installed AND running. The runner checks this first and fails loud with install/start guidance if Docker is missing or its daemon is down; there is no non-Docker fallback.
ffmpeg is REQUIRED (used to extract a 16 kHz mono WAV for Whisper) — the runner checks for it up front and fails loud if it is not on PATH.
Node ≥ 22.

Notes

The container is left running (--restart unless-stopped) for warm reuse; stop with --stop.
If word timestamps are requested but none come back, the runner fails loud (overlay sync depends on them).
See references/ for the Docker lifecycle, the API shape, and the vendoring provenance.