AutoFeed API

Fake Text Video API

Send a story premise. AutoFeed writes the conversation, plays it out message by message on a phone screen, voices both sides and returns the video.

6 to 14 messages per conversation
A separate voice for each side of the thread
Dark or light phone theme, optional video background
Optional earlier messages above the story for context

One Request

This exact body passes the live API schema and costs 1,000 credits, the same as making it in the dashboard.

Request

curl -X POST https://www.autofeed.ai/api/v1/videos \
  -H "Authorization: Bearer $AUTOFEED_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "type": "fake_text",
    "input": {
      "topic": "A son texts his mom that he scratched her new car",
      "numberOfMessages": 10,
      "theme": "dark"
    },
    "webhookUrl": "https://example.com/webhooks/autofeed",
    "idempotencyKey": "order-1042-fake-text"
  }'

202 Accepted

{
  "id": "1c9d6c3e-1f5b-4d2e-9c31-2b8b0f0f9a11",
  "type": "fake_text",
  "status": "processing",
  "costInCredits": 1000,
  "createdAt": "2026-11-02T12:00:00.000Z"
}

Webhook: video.completed

{
  "id": "1c9d6c3e-1f5b-4d2e-9c31-2b8b0f0f9a11",
  "type": "fake_text",
  "status": "completed",
  "error": null,
  "costInCredits": 1000,
  "createdAt": "2026-11-02T12:00:00.000Z",
  "completedAt": "2026-11-02T12:03:41.000Z",
  "url": "https://.../1c9d6c3e-1f5b-4d2e-9c31-2b8b0f0f9a11.mp4"
}

Every Input Field

Read from the API's own schema. Unknown fields are rejected with a 400, never silently dropped.

Field	Type	Default	Notes
`topic`required	string (max 2000)	-	Required. The premise the conversation is written from.
`numberOfMessages`	integer 6-14	10
`historyMode`	"auto" \| "always" \| "never"	"auto"	Whether to show earlier messages above the story: "auto", "always" or "never".
`backgroundCategory`	"None" \| "Minecraft" \| "GTA V" \| "Subway Surfers" \| "Fortnite" \| "Satisfying"	"None"	"None" is the plain phone canvas; the others put a background video behind it.
`theme`	"dark" \| "light"	"dark"
`music`	string (max 255)	"" (none)
`voiceThem`	string	"cgSgspJ2msm6clMCkdW9"	Voice for the other person (left, grey bubbles).
`voiceMe`	string	"TX3LPaxmHKxFdv7VOQHJ"	Voice for the phone owner (right, blue bubbles).
`format`	"9:16" \| "16:9" \| "1:1"	"9:16"

What It Costs

The API is included with Ultimate and spends the same credits as the dashboard. Ultimate's 180k monthly credits cover about 180 requests like the one above. Rendered files are kept for 14 days.

See every Ultimate size →

Fake Text API Questions

Can I write the messages myself?

Not through this type. You send the premise and the message count; the conversation is written for you.

How is a Fake Text video billed?

From the same credit balance as the dashboard, at the same price per video. The cost is in the 202 response before any work starts, and a failed render refunds it.

What the Fake Text API returns