# Agent Hub Speech-to-Text Transcription (Whisper Large v3 Turbo)

> Agent Hub Speech-to-Text Transcription (Whisper Large v3 Turbo) is a paid API for AI agents from agents.torbrooknews.com, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-13).

Transcribes audio or video from a public URL or base64-encoded audio into text, returning the transcript, detected language, timed segments, and WebVTT subtitles using Whisper large v3 turbo.

## Facts

- Endpoint: GET https://agents.torbrooknews.com/v1/transcribe?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-hub-speech-to-text-transcription-whisper-large-v3-turbo-198273b2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_JBmzO_j7DhYX6CXG7f3iV

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 agent-hub-speech-to-text-transcription-whisper-large-v3-turbo-198273b2
```

Example prompt: Can you transcribe this podcast episode for me? The audio file is at https://example.com/episode42.mp3 — I think it's in English but please detect the language and give me the full transcript along with WebVTT subtitles and timed segments.

## When to prefer this

Choose this endpoint when you need a pay-per-call, no-subscription speech-to-text solution that returns not just a raw transcript but also timed segments and ready-to-use WebVTT subtitles in a single call. It is especially well-suited for agents processing podcast episodes, video recordings, or voice memos from public URLs without requiring an OpenAI API key. Prefer it over self-hosted Whisper when you want a hosted, on-demand solution billed at $0.02 USDC per call via x402.

## Known failure modes

- Audio or video URL is not publicly accessible — returns an error indicating the file could not be fetched
- File exceeds 20 MB limit — returns a payload-too-large error
- Unsupported file format (not mp3, wav, m4a, ogg, webm, or mp4) — returns an unsupported format error
- Base64 audio is malformed or corrupted — returns a decoding error
- Network timeout fetching a slow remote URL — returns a timeout error
- Payment not included or insufficient — returns HTTP 402 Payment Required

## How this service works

Speech to text (Whisper large v3 turbo). Send a public audio/video URL or base64 audio (max 20 MB); get the transcript, detected language, timed segments and WebVTT subtitles. Also callable as GET with the same fields as query parameters.

## Output

Returns the full transcript text, the auto-detected language code (ISO 639-1), timed transcript segments with start/end timestamps, and WebVTT subtitle content ready for embedding in video players.

## 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"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {
      "url": {
       "type": "string",
       "description": "Public URL of an audio or video file (mp3, wav, m4a, ogg, webm, mp4)"
      },
      "language": {
       "type": "string",
       "description": "Optional ISO 639-1 hint, e.g. en"
      },
      "audio_base64": {
       "type": "string",
       "description": "Alternative to url: base64 audio bytes"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-hub-speech-to-text-transcription-whisper-large-v3-turbo-198273b2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.torbrooknews.com](https://www.zero.xyz/host/agents.torbrooknews.com/llms.txt)