# DevX Voice Speech-to-Text

> DevX Voice Speech-to-Text is a paid API for AI agents from voice.madebydevx.com, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-29).

Transcribes audio files (or URLs) to text with timestamps, language detection, timed segments, and WebVTT subtitles using Whisper large-v3-turbo; optionally translates to English.

## Facts

- Endpoint: POST https://voice.madebydevx.com/v1/stt?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/devx-voice-speech-to-text-a345a3d5
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_z7hh2sy-aKxwB-NFhbfjY

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 devx-voice-speech-to-text-a345a3d5 -d '<json body>'
```

Example prompt: Can you transcribe this audio file for me — here's the URL: https://example.com/meeting.mp3 — and give me the full transcript along with timestamped segments and WebVTT subtitles? Auto-detect the language.

## When to prefer this

Choose this endpoint when you need high-quality speech-to-text with Whisper large-v3-turbo quality, need WebVTT subtitles or timed segments alongside the transcript, want automatic language detection, or need to translate non-English audio directly to English text. The pay-per-minute USDC pricing (no subscription) and idempotency key support make it ideal for agentic pipelines processing variable audio volumes on Base. Prefer it over generic STT APIs when operating within a crypto-native x402 payment stack or when subtitle generation is required alongside transcription.

## Known failure modes

- Audio URL is not publicly accessible or returns a non-200 status — endpoint returns an error, no charge
- Audio file exceeds 10 MB or 20 minutes — rejected with size/duration error
- Unsupported audio format — returns format error
- Silent audio detected with VAD enabled — not charged, returns empty or minimal transcript
- Invalid base64 encoding — returns parse error
- Network timeout fetching remote audio URL — returns fetch error

## How this service works

Speech to text for agents: send an audio URL, base64 or raw audio (WAV, MP3, FLAC, OGG, M4A, WebM; up to 20 min / 10 MB) and get the transcript, language, timed segments and WebVTT subtitles. Optional task=translate gives English text. $0.002 USDC per started minute on Base; failed or silent audio is not charged. Whisper large-v3-turbo. By DevX.

## Output

A JSON object containing the full transcript text, detected or specified language, an array of timed segments (each with start/end times and text), a WebVTT subtitle string, word count, audio duration in seconds, billed minutes, the model used, task type, and an operation ID. Payment metadata including transaction hash and USDC amount is also returned.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "vad": {
   "type": "boolean",
   "description": "Voice activity detection pre-filter"
  },
  "task": {
   "enum": [
    "transcribe",
    "translate"
   ],
   "type": "string",
   "description": "translate = English output"
  },
  "prompt": {
   "type": "string",
   "maxLength": 500,
   "description": "Optional context words/spelling hints"
  },
  "language": {
   "type": "string",
   "description": "ISO 639-1 code like \"en\", or \"auto\" (default) to detect"
  },
  "audio_url": {
   "type": "string",
   "description": "Public http(s) URL of the audio file (max 10 MB, 20 min)"
  },
  "requestKey": {
   "type": "string",
   "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{7,127}$",
   "maxLength": 128,
   "minLength": 8,
   "description": "Optional idempotency key: the same payer + requestKey + input within 7 days returns the stored result without a second charge."
  },
  "audio_base64": {
   "type": "string",
   "description": "Base64 audio (max 6 MB decoded); a data: URI prefix is allowed"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "result": {
   "vtt": "WEBVTT\n\n00:00.000 --> 00:04.200\nHello from DevX voice. This is a short speech to text demo.",
   "task": "transcribe",
   "text": "Hello from DevX voice. This is a short speech to text demo.",
   "model": "whisper-large-v3-turbo",
   "language": "en",
   "segments": [
    {
     "end": 4.2,
     "text": "Hello from DevX voice. This is a short speech to text demo.",
     "start": 0
    }
   ],
   "word_count": 11,
   "billed_minutes": 1,
   "duration_seconds": 4.28
  },
  "status": "paid",
  "payment": {
   "status": "paid",
   "network": "eip155:8453",
   "tx_hash": "0x0000000000000000000000000000000000000000000000000000000000000000",
   "amount_raw": "2000"
  },
  "operation_id": "6a1f0c7e-2b6d-4f7e-9d2a-0c5b8e1f4a33"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/devx-voice-speech-to-text-a345a3d5/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from voice.madebydevx.com](https://www.zero.xyz/host/voice.madebydevx.com/llms.txt)