# Vaaya Deepgram Transcription

> Vaaya Deepgram Transcription is a paid API for AI agents from vaaya.ai, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Transcribes audio or video files to text using Deepgram Nova-3, with support for speaker diarization, language detection, and timestamped utterances

## Facts

- Endpoint: POST https://vaaya.ai/api/run/deepgram/transcribe
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vaaya-deepgram-transcription-9f9e1a37
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wISbReoQoo3CPuW0OWMhJ

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 vaaya-deepgram-transcription-9f9e1a37 -d '<json body>'
```

Example prompt: Can you transcribe this 45-minute podcast episode for me — the file is at https://example.com/episode42.mp3 — and make sure to label each speaker separately and include timestamps for each segment?

## When to prefer this

Choose this endpoint when you need high-accuracy speech-to-text from audio or video URLs, especially when speaker diarization, language auto-detection, or timestamped utterances are required. Prefer it for podcasts, interview recordings, calls, and voicemails. Best suited for agents that have already staged files to a public URL and need a single API call to get back a structured transcript via x402 micropayment.

## Known failure modes

- Audio URL not publicly reachable — returns error; must pre-upload via files/upload or fal/upload
- Unsupported audio format or corrupt file — transcription fails with format error
- Duration estimate greatly underestimated — may affect pricing calculation
- Language code not supported by Deepgram Nova-3 — fallback or error
- File too large or too long — may time out or require chunking

## How this service works

Transcribe audio (or the audio track of a video) to text with Deepgram Nova-3 — podcasts, calls, voicemails, interviews, screen recordings. Pass `url` (a publicly reachable audio/video file — stage local files via files/upload or fal/upload first) and `duration_minutes` (the approximate length, priced at 1¢/min, default 10). Options: `language` (ISO code, e.g. "en", "hi"), `detect_language: true`, `diarize: true` (speaker labels), `utterances: true` (timestamped segments), `model` ("nova-3" def…

## Output

Returns a full text transcript of the audio or video file, optionally including speaker-labeled segments (diarization), timestamped utterance breakdowns, and detected language metadata, powered by Deepgram Nova-3.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vaaya-deepgram-transcription-9f9e1a37/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from vaaya.ai](https://www.zero.xyz/host/vaaya.ai/llms.txt)