# OpenRouter Audio Transcriptions

> OpenRouter Audio Transcriptions is a paid API for AI agents from OpenRouter at openrouter.mpp.tempo.xyz, paid per call via MPP, price unknown, status unknown (last checked 2026-10-30).

Transcribes base64-encoded PCM WAV audio (mono, 16-bit, 16 kHz, up to 10 minutes) into text using multiple AI models

## Facts

- Endpoint: POST https://openrouter.mpp.tempo.xyz/v1/audio/transcriptions?utm_source=zero.xyz
- Price: price unknown
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Provider: OpenRouter
- Docs: https://openrouter.ai
- Website: https://openrouter.ai
- Tags: llm, unified, multi-model, chat, ai
- Canonical page: https://www.zero.xyz/c/openrouter-audio-transcriptions-16fad4d9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_9n-Xz_Cr9XUiI60o8D4Sj

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 openrouter-audio-transcriptions-16fad4d9 -d '<json body>'
```

Example prompt: Can you transcribe this WAV audio recording I have — it's a mono 16-bit 16kHz file, about 3 minutes long — and give me the full text of what was said?

## When to prefer this

Choose this endpoint when you need to transcribe PCM WAV audio files (mono, 16-bit, 16 kHz) using a choice of AI models with live pricing transparency via OpenRouter. Ideal when you want model flexibility for speech-to-text without being locked into a single provider, or when you need to compare transcription quality and cost across models. Best suited for audio clips up to 10 minutes that can be base64-encoded.

## Known failure modes

- Audio not in expected format (must be base64 PCM WAV, mono, 16-bit, 16 kHz) — returns format error
- Audio exceeds 10-minute limit — rejected with duration error
- Invalid or unsupported model specified — returns model not found error
- Malformed base64 encoding — returns decoding error
- Insufficient funds or payment failure — returns payment required error
- Empty or silent audio — may return empty transcript or low-confidence result

## How this service works

Transcribe base64 PCM WAV (mono, 16-bit, 16 kHz, up to 10 minutes; models and prices at GET /v1/audio/models)

## Output

A text transcript of the spoken content from the submitted audio, extracted by an AI speech recognition model. The response contains the recognized words and sentences from the audio recording.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/openrouter-audio-transcriptions-16fad4d9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from openrouter.mpp.tempo.xyz](https://www.zero.xyz/host/openrouter.mpp.tempo.xyz/llms.txt)