API reference · YouTube

youtube/bulk/video-transcript

Integrate this model through SandBase's unified API, with production-ready schemas and examples.

APIAsyncOpen model

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDyoutube/bulk/video-transcript

Input Schema

7 parameters · 0 required · 7 optional

Parameter	Type	Required	Description
`end_date`	string	Optional	End date for filtering videos by upload date (format: YYYY-MM-DD or ISO 8601, optional). Only applicable and used with channel_url; ignored for youtube_url. Videos uploaded on or before this date will be fetched.
`language`	string	Optional	Language of the subtitles in ISO 639-1 format, e.g., `en`, `fr`. Applicable to both youtube_url and channel_url. Leave blank for default language.
`max_videos`	integer	Optional	Maximum number of videos to fetch from the channel (optional, default: 10, range: 1 to 200). Only applicable and used with channel_url; ignored for youtube_url. Combine with start_date/end_date for filtered results. · Min: 1 · Max: 200 · Default: 10
`start_date`	string	Optional	Start date for filtering videos by upload date (format: YYYY-MM-DD or ISO 8601, optional). Only applicable and used with channel_url; ignored for youtube_url. Videos uploaded on or after this date will be fetched.
`channel_url`	string	Optional	Enter a valid YouTube channel URL (e.g., https://www.youtube.com/channel/UCxxxxxxxxxxxxxxxxxxxxxx or https://www.youtube.com/@channelhandle). Use this to fetch videos from the channel, paired with 'max_videos', 'start_date', and 'end_date' for limiting and filtering results.
`youtube_url`	string	Optional	Enter a valid YouTube video URL (e.g., https://www.youtube.com/watch?v=video_id, https://youtu.be/video_id, or https://www.youtube.com/shorts/video_id). Use this for fetching a single video, paired with 'language' for transcript. Do not combine with channel filtering fields.
`include_transcript_text`	boolean	Optional	Include the full transcript as a plain string without timestamps (transcript_text field). Default is off to reduce response size. Enable this if you need the transcript as a single text block. · Default: false

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "youtube/bulk/video-transcript",
  "max_videos": 10,
  "include_transcript_text": false,
  "prompt": "a beautiful sunset over mountains"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to YouTube Video Transcript