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

> Agent Hub Speech-to-Text (Whisper Large v3 Turbo) is a paid API for AI agents from agents.torbrooknews.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-13).

Transcribes audio files or public audio URLs to text using Whisper large v3 turbo, returning output in json, text, srt, vtt, or verbose_json formats

## Facts

- Endpoint: GET https://agents.torbrooknews.com/v1/audio/transcriptions?utm_source=zero.xyz
- Price: $0.01/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-whisper-large-v3-turbo-1b181010
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap__SUzz0EEzLmv92V2jwTHu

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-whisper-large-v3-turbo-1b181010
```

Example prompt: Can you transcribe the audio at https://example.com/recording.mp3 and give me the result as an SRT subtitle file?

## When to prefer this

Choose this endpoint when you need a flat-rate ($0.01 USDC), no-API-key speech-to-text solution compatible with the OpenAI Whisper API, especially when you want multiple output formats (SRT, VTT, verbose_json) or need to transcribe from a public URL without uploading a file. Prefer over OpenAI directly when avoiding API key management or when cost predictability matters.

## Known failure modes

- Audio file exceeds 20 MB limit — request rejected
- Invalid or inaccessible public URL — cannot fetch audio
- Unsupported audio format — transcription fails
- Incorrect response_format value — may return error or default format
- Network timeout for large files — partial or no response

## How this service works

OpenAI-compatible speech to text (Whisper large v3 turbo): multipart file upload exactly like OpenAI /v1/audio/transcriptions, with response_format json, text, srt, vtt or verbose_json. Also accepts a public audio url. Up to 20 MB, flat price, no API key. Also callable as GET with the same fields as query parameters.

## Output

Returns the transcription of the audio in the requested format: plain text ('text'), JSON object with a 'text' field ('json'), SRT subtitle format ('srt'), WebVTT subtitle format ('vtt'), or a detailed JSON object including segments and timestamps ('verbose_json').

## 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",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "Public audio file URL"
      },
      "language": {
       "type": "string"
      },
      "response_format": {
       "type": "string",
       "description": "json | text | srt | vtt | verbose_json"
      }
     }
    }
   },
   "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-whisper-large-v3-turbo-1b181010/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)