Chat with a YouTube video

Ask questions about a YouTube video using its file_id.

Complete Workflow:

Step 1: Ingest the YouTube video

curl --request POST \
  --url https://api.skimming.ai/ingest/v1/api/youtube \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "url": "https://www.youtube.com/watch?v=VIDEO_ID"
  }'

Step 2: Chat with the video

curl --request POST \
  --url https://api.skimming.ai/chat/v1/api/video/youtube \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "file_id": "abc123-def456-ghi789",
    "question": "What are the main points in this video?",
    "streaming": false
  }'

POST /chat/v1/api/video/youtube

Chat with a YouTube video

cURL

curl --request POST \
  --url https://api.skimming.ai/chat/v1/api/video/youtube \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "file_id": "abc123-def456-ghi789",
  "question": "What are the main points discussed in this video?",
  "streaming": false,
  "model": "gpt-4",
  "model_type": "openai"
}
'

200

"<string>"

Authorizations

Authorization · string · header · required

Bearer token authentication using an API key

Body

application/json

file_id · string · required

The file_id returned from ingest endpoint

Example:

"abc123-def456-ghi789"

question · string · required

Your question about the content

Example:

"What are the main points discussed in this document?"

streaming · boolean · default: true

Whether to stream the response (SSE format)

model · enum<string> · default: gpt-4

AI model to use

Available options: gpt-4, gpt-4o, gpt-4o-mini, gpt-3.5-turbo, claude-3-opus, claude-3-sonnet, claude-3.5-sonnet, gemini-1.5-pro, gemini-1.5-flash

Example:

"gpt-4"

model_type · enum<string> · default: openai

Model provider

Available options: openai, anthropic, gemini

Example:

"openai"

conversation_type · enum<string> · default: single

Type of conversation

Available options: single, group

max_output · integer

Maximum output tokens

Example:

2000

Response

200

text/event-stream

Successful response

Server-Sent Events stream (when streaming=true)