# agentic.no nb-whisper-large Audio Transcription

> agentic.no nb-whisper-large Audio Transcription is a paid API for AI agents from wayd-1650.agentic.no, paid per call via x402, $0.004/call, status down (last checked 2026-10-21).

Transcribes audio files to text using the nb-Whisper large model via an OpenAI-compatible API endpoint

## Facts

- Endpoint: POST https://wayd-1650.agentic.no/m/nb-whisper-large/v1/audio/transcriptions?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: down
- Last checked: 2026-10-21
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentic-no-nb-whisper-large-audio-transcription-08712302
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_QH4_Hw9-HdayYECju8qAE

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 agentic-no-nb-whisper-large-audio-transcription-08712302 -d '<json body>'
```

Example prompt: Can you transcribe this audio file for me into text? It's a Norwegian recording, so make sure to use Norwegian as the language.

## When to prefer this

Choose this endpoint when you need accurate speech-to-text transcription, especially for Norwegian-language audio, and require an OpenAI-compatible API interface. The nb-Whisper large model is specifically fine-tuned for Norwegian, making it superior to generic Whisper deployments for Norwegian content. Prefer this over generic transcription services when Norwegian accuracy is critical, or when you need a pay-per-use model with no subscription commitment via x402 micropayments.

## Known failure modes

- Unsupported audio format results in an error response
- Audio file too large or too long may cause timeout or rejection
- Heavily accented or noisy audio may produce inaccurate transcriptions
- Missing or malformed file field returns a 400 bad request
- Network or service unavailability returns a 5xx error
- Non-Norwegian audio may yield lower accuracy given the model's fine-tuning focus

## How this service works

agentic.no inference: OpenAI-compatible audio transcription (POST /v1/audio/transcriptions)

## Output

A text transcription of the submitted audio file, containing the recognized speech as written text, optionally formatted according to the specified response_format (e.g. plain text or JSON).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "file": {
   "type": "string",
   "description": "the audio file part"
  },
  "language": {
   "type": "string"
  },
  "response_format": {
   "type": "string"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentic-no-nb-whisper-large-audio-transcription-08712302/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from wayd-1650.agentic.no](https://www.zero.xyz/host/wayd-1650.agentic.no/llms.txt)