# AssemblyAI Speech Transcription via OpenRouter

> AssemblyAI Speech Transcription via OpenRouter is a paid API for AI agents from AssemblyAI at assemblyai.mpp.tempo.xyz, paid per call via MPP, price unknown, status unknown (last checked 2026-10-29).

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

## Facts

- Endpoint: POST https://assemblyai.mpp.tempo.xyz/v1/audio/transcriptions?utm_source=zero.xyz
- Price: price unknown
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Provider: AssemblyAI
- Docs: https://openrouter.ai
- Website: https://openrouter.ai
- Tags: ai
- Canonical page: https://www.zero.xyz/c/assemblyai-speech-transcription-via-openrouter-92d25f69
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wIg4tMwREzVSOtZ5om5bS

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 assemblyai-speech-transcription-via-openrouter-92d25f69 -d '<json body>'
```

Example prompt: Can you transcribe this audio recording for me? I have a base64-encoded mono 16 kHz PCM WAV file of a 5-minute interview I need converted to text using AssemblyAI.

## When to prefer this

Choose this endpoint when you need to transcribe short-to-medium audio clips (up to 10 minutes) encoded as base64 PCM WAV at 16 kHz mono, especially when using AssemblyAI's recognition quality via a single-call payment model through OpenRouter's infrastructure.

## Known failure modes

- Audio not in correct format (must be mono, 16-bit, 16 kHz PCM WAV) returns a format error
- Audio exceeds 10-minute limit returns a duration error
- Invalid or malformed base64 encoding causes a decoding failure
- Unsupported or unavailable model selection returns a model error
- Payment or authentication failure prevents processing

## 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

Returns a text transcript of the spoken content in the submitted audio file, produced by AssemblyAI's speech recognition models.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/assemblyai-speech-transcription-via-openrouter-92d25f69/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from assemblyai.mpp.tempo.xyz](https://www.zero.xyz/host/assemblyai.mpp.tempo.xyz/llms.txt)