# Automaton Media APIs – Speech-to-Text Transcription

> Automaton Media APIs – Speech-to-Text Transcription is a paid API for AI agents from api.language123.net, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-10).

Transcribes audio or video from a public URL into text, SRT, VTT, or JSON format, with optional summarization and translation, paid per-request via USDC.

## Facts

- Endpoint: POST https://api.language123.net/v1/transcribe?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/automaton-media-apis-speech-to-text-transcription-5625c97d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Ogi7shEw_wpShLgPDWYdg

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 automaton-media-apis-speech-to-text-transcription-5625c97d -d '<json body>'
```

Example prompt: Transcribe this YouTube video for me — https://www.youtube.com/watch?v=abc123 — and give me the output as an SRT subtitle file in English, using Whisper for accuracy.

## When to prefer this

Choose this endpoint when you need pay-per-use transcription without account setup or API keys, especially when working with YouTube URLs, podcasts, or direct audio/video links. The 'any' mode is faster by leveraging platform captions; 'whisper' mode gives higher accuracy. Prefer this over managed transcription services when cost predictability per call and USDC micro-payment via x402 on Base are required. Also useful when you need transcription plus summarization or multi-language translation in a single call.

## Known failure modes

- URL is not publicly accessible or behind authentication — returns error
- Unsupported media format or codec at the provided URL
- Duration too long or file too large — may time out or be rejected
- Language detection fails for very short or noisy audio
- Translation quota exceeded if more than 3 target languages requested
- Payment not confirmed via x402 — request rejected before processing

## How this service works

Pay-per-use APIs for AI agents: YouTube and audio transcription (speech-to-text); Text-to-speech: natural English voices (MP3/WAV); Text-to-image generation; Web scraper: any URL to clean Markdown; YouTube transcript (captions, instant). Pay each request with USDC via x402 on Base - no signup, no API key.

## Output

Returns a JSON object containing the video or audio title, the output format (txt, srt, vtt, or json), the detected or specified language code, the full transcript in the requested format, and the media duration in seconds.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public media URL (YouTube, podcast, direct audio/video link)"
  },
  "mode": {
   "enum": [
    "any",
    "whisper"
   ],
   "type": "string",
   "description": "any = allow platform captions (faster)"
  },
  "format": {
   "enum": [
    "txt",
    "srt",
    "vtt",
    "json"
   ],
   "type": "string"
  },
  "language": {
   "type": "string",
   "description": "auto or ISO 639-1 code"
  },
  "summarize": {
   "type": "boolean"
  },
  "translate_to": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "maxItems": 3
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "title": "…",
  "format": "srt",
  "language": "en",
  "transcript": "1\n00:00:00,000 --> …",
  "duration_sec": 212
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/automaton-media-apis-speech-to-text-transcription-5625c97d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.language123.net](https://www.zero.xyz/host/api.language123.net/llms.txt)