YouTube Video English Transcript with Video and Channel Details
omnial/youtube-transcript-and-video-details-english
Given one YouTube video address, returns the video's English transcript as timed lines, each with its text, start, end and duration in seconds, and as one plain block of text, together with the video's title, description, id, watch and thumbnail links, length, publication time, view, like and comment counts, the subtitle language chosen and those on offer, whether the transcript was auto-generated, a status word, and the channel's id, name, handle and avatar link. One video per call.
activeper resultv1
Price
Up to $0.00683 per result; you pay what the call used
The price shown is the price you pay. No monthly minimum. Top-ups start at $5.
Data source
YouTube
Data from YouTube.
Use it
Five steps: search, inspect, learn, run, settle. No per-tool setup; your agent reaches this tool through the meta-tools it already has.
agent
// 1. search: find the tool
omnial_search({ query: "what you need" })
// 2. inspect: price and input schema
omnial_inspect({ tool: "omnial/youtube-transcript-and-video-details-english" })
// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "omnial/youtube-transcript-and-video-details-english" })
// 4. run: price the exact call first, then run it
omnial_execute({ tool: "omnial/youtube-transcript-and-video-details-english", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "omnial/youtube-transcript-and-video-details-english", input: { /* ... */ } })
// 5. settle: the call is charged when it finishes, nothing to doNot connected yet? Point your MCP client at https://mcp.eden-engine.com/mcp, then copy a config for your client.
Pricing
Every charge this tool can incur.
| Charge | Price |
|---|---|
Per result Charged for every result returned | $0.00683 |
- Updated
- Oct 17, 2026
Input and output schemas
Input schema
input_schema.json
{
"type": "object",
"required": [
"youtube_url",
"language"
],
"properties": {
"language": {
"enum": [
"en"
],
"type": "string",
"description": "The subtitle language to fetch, as a two-letter code; only English is offered."
},
"max_videos": {
"enum": [
1
],
"type": "integer",
"default": 1,
"description": "How many videos to read. The supplier applies this only to its channel mode, which is not offered here, so a call reads the one video addressed; only 1 is offered."
},
"youtube_url": {
"type": "string",
"pattern": "^(https?://)?(www\\.)?(youtube\\.com/(watch\\?v=|embed/|v/|shorts/)|youtu\\.be/)[a-zA-Z0-9_-]{11}(\\?.*)?$",
"description": "The address of the YouTube video to transcribe: a watch, embed, short-link or Shorts address carrying the video's eleven-character id."
},
"include_transcript_text": {
"enum": [
true
],
"type": "boolean",
"default": true,
"description": "Whether to also return the whole transcript as one plain block of text; only on is offered, so the block is always returned."
}
},
"additionalProperties": false
}Output schema
output_schema.json
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"url": {
"type": [
"string",
"null"
],
"description": "The video's own youtube.com link."
},
"title": {
"type": [
"string",
"null"
],
"description": "The video's title."
},
"status": {
"type": "string",
"description": "The supplier's status word for the call."
},
"video_id": {
"type": "string",
"description": "The video's eleven-character id."
},
"thumbnail": {
"type": [
"string",
"null"
],
"description": "A link to the video's thumbnail image."
},
"channel_id": {
"type": "string",
"description": "The channel's id."
},
"like_count": {
"type": "number",
"description": "How many likes the video has."
},
"transcript": {
"type": "array",
"items": {
"type": "object",
"properties": {
"end": {
"type": "number",
"description": "When the line ends, in seconds."
},
"text": {
"type": [
"string",
"null"
],
"description": "The line as spoken."
},
"start": {
"type": "number",
"description": "When the line starts, in seconds."
},
"duration": {
"type": "number",
"description": "How long the line is on screen, in seconds."
}
}
},
"description": "The transcript as timed lines, in order."
},
"view_count": {
"type": "number",
"description": "How many times the video was viewed."
},
"description": {
"type": [
"string",
"null"
],
"description": "The video's description text, with any links removed."
},
"channel_name": {
"type": "string",
"description": "The channel's display name."
},
"published_at": {
"type": "string",
"description": "When the video was published, as a timestamp."
},
"comment_count": {
"type": "number",
"description": "How many comments the video has."
},
"transcript_text": {
"type": [
"string",
"null"
],
"description": "The whole transcript as one plain block of text, without timestamps."
},
"channel_username": {
"type": "string",
"description": "The channel's handle."
},
"duration_seconds": {
"type": "number",
"description": "How long the video runs, in seconds."
},
"channel_thumbnail": {
"type": [
"string",
"null"
],
"description": "A link to the channel's avatar image."
},
"is_auto_generated": {
"type": "boolean",
"description": "Whether the returned transcript was generated automatically."
},
"selected_language": {
"type": "string",
"description": "The subtitle language the call returned, by name."
},
"available_languages": {
"type": "array",
"items": {
"type": "string"
},
"description": "The subtitle languages the video offers, by name."
}
}
},
"description": "One entry: the video asked for."
}
},
"description": "The video and its transcript, as a one-entry list after shaping."
}