Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.clearmaas.com/llms.txt

Use this file to discover all available pages before exploring further.

Audio input is supported by Gemini multimodal models. Two paths:

​
Path 1: OpenAI-shape input_audio on /v1/chat/completions

The gateway translates the OpenAI input_audio content part to Gemini’s inline_data automatically. The format field maps to the right MIME type (mp3 → audio/mp3, wav → audio/wav, etc.). 
curl https://api.clearmaas.com/v1/chat/completions \
  -H "Authorization: Bearer sk-clearmaas-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.5-flash",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "What is happening in this audio clip?"},
        {"type": "input_audio", "input_audio": {"data": "<base64>", "format": "mp3"}}
      ]
    }]
  }'

​
Path 2: Native /v1beta/ with inline_data

If you’re already on Gemini’s native protocol, pass inline_data directly — no translation involved. 
curl "https://api.clearmaas.com/v1beta/models/google/gemini-2.5-flash:generateContent" \
  -H "Authorization: Bearer sk-clearmaas-..." \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [
        {"text": "What is happening in this audio clip?"},
        {"inline_data": {"mime_type": "audio/mp3", "data": "<base64>"}}
      ]
    }]
  }'

​
Supported model families

Gemini multimodal models accept inline audio — for example google/gemini-2.5-flash and the Gemini 3.x line. Behavior matches Google’s published Gemini API exactly.

​
Limits

Inline audio payloads are size-capped by the upstream provider. For longer files, the provider’s own File API (uploaded outside ClearMaas against the provider directly) is the typical workaround. Check Google’s Gemini API documentation for current size and duration limits.

​
See also