---
title: "gemini-audio-vision"
method: POST
path: "/api/v1/gemini-audio-vision"
tags: ["LLM / Multimodal"]
---

# gemini-audio-vision

`POST /api/v1/gemini-audio-vision`

## Request

- Base URL: `https://api.muapi.ai`
- URL: `https://api.muapi.ai/api/v1/gemini-audio-vision`
- Auth: one of:
  - API key in header `x-api-key`
  - OAuth 2 (client credentials, token URL `https://api.muapi.ai/oauth/token`)

Analyze and describe audio content using Google Gemini's native audio understanding. Input: text prompt, audio_url, optional system_prompt, model (gemini-2.5-flash). Output: detailed text analysis. Use for: transcription QA, audio content moderation, speaker/tone analysis, podcast summarization, sound-event detection.

## Query parameters

- `webhook` string
- `team_id` integer, nullable

## Headers

- `x-api-key` string
- `x-embed-code` string, nullable
- `x-agent-embed-code` string, nullable
- `x-whitelabel-studio` string, nullable
- `authorization` string, nullable

## Request body

- GeminiAudioVisionRequest
  - `prompt` string, required
  - `audio_url` string, uri, required
  - `system_prompt` string, nullable
  - `model` 'gemini-2.5-flash'
  - `webhook_url` string, uri, nullable

## Response `200`

Successful Response

- unknown

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/muapi/apis/muapi-api.md) · [All operations](https://skmtc.dev/muapi/apis/muapi-api/llms.txt) · [OpenAPI document](https://skmtc.dev/muapi/apis/muapi-api/revisions/e4b7374381e5?raw)