# pagos.andreax.dev Audio Transcription (Whisper LOCAL)

> pagos.andreax.dev Audio Transcription (Whisper LOCAL) is a paid API for AI agents from pagos.andreax.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Transcribes an audio file to text using a locally-run Whisper model, with automatic language detection and optional language hint.

## Facts

- Endpoint: GET https://pagos.andreax.dev/api/taller/peaje/transcribir
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pagos-andreax-dev-audio-transcription-whisper-local-5bbb5a58
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_BKTYDNgBf5LeB7CmN5Dfq

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 pagos-andreax-dev-audio-transcription-whisper-local-5bbb5a58
```

Example prompt: Can you transcribe this voice note for me? Here's the audio as a base64 string: [audio_b64] — it's in Spanish.

## When to prefer this

Choose this endpoint when you need local Whisper-based transcription with automatic language detection, particularly for Spanish or multilingual audio, and want a cost-effective per-call price of $0.01 USDC. Prefer this over cloud-based STT APIs when data privacy is a concern or when you want predictable per-transcription pricing via x402 micropayments.

## Known failure modes

- Invalid or corrupted base64 audio data returns an error
- Unsupported audio format may cause transcription failure
- Very long audio files may time out
- Missing required archivo_b64 parameter returns a validation error
- Inaudible or noisy audio may produce inaccurate transcription

## How this service works

Transcribe un archivo de audio a texto (voz a texto) con Whisper LOCAL, detección automática de idioma. Para agentes que procesan notas de voz, llamadas o podcasts. Sube el audio por multipart o como 'archivo_b64'. Opcional 'lang' (es|en|...).

## Output

Returns the transcribed text of the audio input, along with the detected or specified language. The transcript is a plain-text representation of the spoken content in the audio file.

## 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",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "archivo_b64"
     ],
     "properties": {
      "lang": {
       "type": "string",
       "description": "Idioma ISO (es, en, ...) — opcional"
      },
      "archivo_b64": {
       "type": "string",
       "description": "Audio en base64 (o subir 'archivo' por multipart)"
      }
     }
    }
   },
   "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/pagos-andreax-dev-audio-transcription-whisper-local-5bbb5a58/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from pagos.andreax.dev](https://www.zero.xyz/host/pagos.andreax.dev/llms.txt)