# Audio & Podcast Transcriber

> Audio & Podcast Transcriber is a paid API for AI agents from 2-29-135-242.sslip.io, paid per call via x402, $0.02/call, status unknown (last checked 2026-11-21).

Transcribes audio/video files and podcast feeds to text using faster-whisper speech recognition, with filtering and vocabulary hints

## Facts

- Endpoint: POST https://2-29-135-242.sslip.io/x402/audio-podcast-transcriber?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-21
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/audio-podcast-transcriber-f05004d2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_khD32Tep-gEog9a9-eb0S

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 audio-podcast-transcriber-f05004d2 -d '<json body>'
```

Example prompt: Can you transcribe the 3 most recent episodes of this podcast feed https://feeds.megaphone.fm/ROOSTERTEETH7199270178 using the 'base' model and skip any episodes with 'trailer' in the title?

## When to prefer this

Choose this endpoint when you need to convert spoken audio — from direct file URLs, podcast RSS feeds, or Apple Podcasts links — into text at low cost ($0.02/call). It's particularly well-suited for batch podcast transcription with filtering by date, episode count, or title keywords. Prefer this over general-purpose transcription services when you need podcast-specific features like RSS feed support, episode filtering, and vocabulary hints for specialized terminology.

## Known failure modes

- Invalid or inaccessible audio/video URL returns an error or empty result
- Private or paywalled podcast feeds cannot be fetched and will fail
- Very long episodes may time out or take many minutes to process
- Unsupported audio format may cause processing failure
- Apple Podcasts URL resolution may fail if feed is not publicly available
- Language mismatch without explicit language code may reduce transcription accuracy
- vocabulary hint exceeding 400 characters will be rejected or truncated

## How this service works

Fast tools (web read, domain RDAP/DNS/SSL, Federal Register, clinical trials, OSV vulnerabilities, literature, e-mail auth) and data APIs on official/open data (leads, tenders, SEC filings, VAT, geocoding, aviation...). POST JSON, pay per call in USDC on Base via x402. Charged only when results are returned.

## Output

Returns a JSON object with a count of transcribed items and an array of result objects, each containing the transcript text and associated metadata (episode title, URL, publication date, etc.) for each processed audio file or podcast episode.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "urls": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "example": [
    "https://archive.org/download/childrensshortworks09_1010_librivox/childrensshortworks009_lionandthehare_ab.mp3"
   ],
   "description": "Direct links to audio or video files (mp3, m4a, wav, ogg, flac, mp4, webm, ...) or public podcast RSS feed URLs, or Apple Podcasts show links (podcasts.apple.com/.../id123; the public RSS feed is found automatically). For a feed the newest episodes are transcribed (see Max episodes per feed)."
  },
  "model": {
   "enum": [
    "tiny",
    "base",
    "small"
   ],
   "type": "string",
   "example": "base",
   "description": "Speech recognition model (faster-whisper, runs on CPU inside the actor). tiny = fastest, base = good English quality at high speed (default), small = better accuracy and other languages, slower."
  },
  "language": {
   "type": "string",
   "description": "Two-letter language code of the audio, for example en, de, es, fr, bg. Leave empty to detect the language automatically for each file."
  },
  "vocabulary": {
   "type": "string",
   "description": "Names, brands or special terms spoken in the audio, comma separated, e.g. Apify, Kubernetes, Varna. Whisper uses them as a hint to spell them correctly. Max 400 characters. Empty = no hint."
  },
  "maxEpisodes": {
   "type": "integer",
   "example": 1,
   "description": "How many of the newest episodes to transcribe from each podcast RSS feed. Ignored for direct file URLs. Long episodes take long: about 1 hour of audio per few minutes of run time."
  },
  "episodesSince": {
   "type": "string",
   "description": "Podcast feeds only: keep episodes published on or after this date (YYYY-MM-DD) or within a period like '30 days', '2 weeks' or '3 months'. Applied before Max episodes per feed. Empty = no date filter."
  },
  "titleExcludes": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "Podcast feeds only: skip episodes whose title contains one of these texts (case-insensitive), e.g. trailer, rerun, best of."
  },
  "titleIncludes": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "Podcast feeds only: transcribe only episodes whose title contains one of these texts (case-insensitive). * matches anything, e.g. interview*ceo. Empty = all titles."
  },
  "subtitleMaxChars": {
   "type": "integer",
   "example": 42,
   "description": "Max characters per subtitle line 
… (truncated)
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "count": 1,
  "items": [
   {
    "...": "one result object"
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/audio-podcast-transcriber-f05004d2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from 2-29-135-242.sslip.io](https://www.zero.xyz/host/2-29-135-242.sslip.io/llms.txt)
