Conversions across 221 color spaces, tested against cited sources: CSS strings, gamut, LUTs
Nothing to run from here
YouTube Dubbing is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
12
tools declared
—
trust score
local
runs on your machine
—
calls last 7d
What it does
AI dubbing for YouTube videos: one cloned voice per speaker, synced SRT, YouTube audio tracks.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'MIRAGEA_API_KEY=${MIRAGEA_API_KEY}' --transport stdio youtube-dubbing-mcp '--' docker run -i --rm --platform linux/amd64 -e MIRAGEA_API_KEY docker.io/miragea/youtube-dubbing-mcp:0.1.0
# 2 — ask your agent for something these tools do
# dubbing_check_setup, dubbing_list_voices, dubbing_start_project and 9 more
It needs MIRAGEA_API_KEY: this reads it from your environment, so export it first.
YouTube Dubbing costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
RTAll 2 servers
rty2345rr2 servers
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts YouTube Dubbing as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It has not been scanned here, so read the surface, and its source, before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Docker installed and running. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads MIRAGEA_API_KEY (Voice engine API key from https://miragea.ai/workspace/api) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx MIRAGEA_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'MIRAGEA_API_KEY=${MIRAGEA_API_KEY}' --transport stdio youtube-dubbing-mcp '--' docker run -i --rm --platform linux/amd64 -e MIRAGEA_API_KEY docker.io/miragea/youtube-dubbing-mcp:0.1.0Reconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own image: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: MIRAGEA_API_KEY — Voice engine API key from https://miragea.ai/workspace/api. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
12 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Check that dubbing will work: API key set (value hidden), voice engine reachable, its voice models and limits, ffmpeg and yt-dlp available, and where projects are saved. Read-only; creates no job. Call first.
Takes no parameters.
List the voices saved in the user's Miragea account (actor_id, name, language) to use with dubbing_set_voice. Read-only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| offset | integer | no | — |
Start a dubbing project from a YouTube URL, a local video/audio file, or an SRT/VTT caption file. Downloads the audio (and optionally the video for a preview), takes the transcript from YouTube captions when available or transcribes the speech, merges caption fragments into sentences and labels…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source | string | yes | — |
| source_language | string | no | — |
| captions_file | string | no | — |
| prefer_captions | boolean | no | — |
| download_video | boolean | no | — |
| num_speakers | integer | no | — |
| project_name | string | no | — |
Read a project's transcript in pages: id, speaker, start, slot_seconds and text. With target_language, each line also gets target_chars and max_chars, the length that fits its time slot when spoken in that language, plus any translation already saved. Use it to review speakers and to translate.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
| target_language | string | no | — |
| offset | integer | no | — |
| limit | integer | no | — |
Set who speaks each segment. assignments maps a segment id ('7'), an inclusive range ('7-12') or '*' (all) to a speaker name, e.g. {'1-4': 'Anna', '5': 'Ben'}. Use when captions had no speaker markers.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
| assignments | object | yes | — |
Cut a clean 4-14 second voice sample for each speaker from the source audio, with its transcript. With share=true each sample is uploaded to a temporary public file host (uguu.se, deleted after a few hours) so the voice engine can clone it, and the speaker's voice is set automatically. Ask the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
| speakers | array | no | — |
| share | boolean | no | — |
Choose the voice for one speaker: a saved voice (actor_id from dubbing_list_voices) or a voice to clone from a public reference_audio_url (6-15 s of clean speech) with its exact reference_text. Optional model ('expressive' or 'standard') and speed (0.25-4).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
| speaker | string | yes | — |
| actor_id | string | no | — |
| reference_audio_url | string | no | — |
| reference_text | string | no | — |
| model | string | no | — |
| speed | number | no | — |
Save translated lines for a target language as {segment_id: text} (all at once or in batches; later calls update only the ids given), plus an optional localized YouTube title and description. Returns a fit check: lines that are too long for their time slot, and ids still missing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
| language | string | yes | — |
| translations | object | yes | — |
| title | string | no | — |
| description | string | no | — |
| max_speedup | number | no | — |
Voice every translated line with its speaker's voice, then build the dubbed audio track at the exact video length (each line starts with the original; lines are sped up only when needed, max_speedup 1.0-1.5), the translated SRT, and a preview MP4 when the video was downloaded. Optional background:…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
| language | string | yes | — |
| max_speedup | number | no | — |
| model | string | no | — |
| audio_format | string | no | — |
| background_file | string | no | — |
| background_volume | number | no | — |
| preview_video | boolean | no | — |
Write the YouTube upload package: one folder per language with audio.m4a (the dub track, video length), captions.srt, title.txt and description.txt, plus UPLOAD-TO-YOUTUBE.md with the YouTube Studio > Languages steps and a Studio link. The YouTube API cannot upload audio tracks, so the user…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
| languages | array | no | — |
Show a project's state: speakers and their voices, languages translated and rendered, output paths.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | — |
List dubbing projects saved on this machine, newest first.
Takes no parameters.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install YouTube Dubbing or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
—Grade not published
No rule-by-rule report on file for this release
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing ships as a container image. The scanner reads packages on npm and PyPI and public source; an image is neither, so there is no grade here — not a withheld one, an unmeasured one.
Release history
It installs from a container image rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 0.1.0.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish YouTube Dubbing can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.