# AgentUtility Video Transcription (Whisper v3)

> AgentUtility Video Transcription (Whisper v3) is a paid API for AI agents from x402.agentutility.ai, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-15, last successful call 2026-09-05).

Transcribes any video URL to text using Whisper v3 large, with auto-detection of 90+ languages, optional English translation, and optional speaker diarization.

## Facts

- Endpoint: POST https://x402.agentutility.ai/video-transcribe
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Last successful call: 2026-09-05
- Success rate: 33% of calls made through Zero
- Activations on Zero: 18
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentutility-video-transcription-whisper-v3-83d051eb
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_0zzrAem-SZEeXvwrvtIhJ

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agentutility-video-transcription-whisper-v3-83d051eb -d '<json body>'
```

Example prompt: Transcribe this video for me — https://example.com/my-lecture.mp4 — it's in French but I want the transcript translated into English, and please separate out different speakers if you can.

## When to prefer this

Choose this endpoint when you need high-accuracy transcription of a video file via URL, especially for multilingual content, foreign-language-to-English translation, or meeting recordings needing speaker attribution. It leverages Whisper v3 large, the highest-accuracy open model, and handles up to 60 minutes per call. Prefer it over generic STT APIs when language auto-detection or diarization is needed without pre-configuration.

## Known failure modes

- Video URL unreachable or returns non-200 — transcription fails with URL error
- Video exceeds 60-minute or 500 MB limit — rejected with size/duration error
- Unsupported audio codec or corrupted video file — returns processing error
- Language not among the 90+ supported — may produce garbled output
- Network timeout fetching large video files — request may time out

## How this service works

Transcribes any video URL to text with Whisper v3 large. Auto-detects 90+ languages and offers a translate-to-English mode. 60-min / 500MB max. Same backend as video-to-text under a clearer slug. Use it for video transcription, video to audio transcription, or video-to-text. For speaker labels, use the speaker-diarize endpoint.

## Output

Returns the full text transcript of the video's spoken audio, including detected source language, optionally translated to English, with optional per-speaker segment labels and timestamps. Maximum video length is 60 minutes / 500 MB.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "required": [
      "media_url"
     ],
     "properties": {
      "task": {
       "enum": [
        "transcribe",
        "translate"
       ],
       "type": "string",
       "description": "'transcribe' (default) keeps original language, or 'translate' to English."
      },
      "language": {
       "type": "string",
       "description": "Source language hint (ISO code). Optional; auto-detected if omitted."
      },
      "media_url": {
       "type": "string",
       "description": "URL of the video or audio file to transcribe. Max 60 minutes / 500MB."
      }
     }
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "task": {
       "type": "string"
      },
      "text": {
       "type": "string"
      },
      "duration_seconds": {
       "type": "integer"
      }
     }
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "task": "transcribe",
  "text": "Hello world.",
  "duration_seconds": 23
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentutility-video-transcription-whisper-v3-83d051eb/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.agentutility.ai](https://www.zero.xyz/host/x402.agentutility.ai/llms.txt)