Google Gemini API — AI 视频、图像和文本转语音

1. 使用 Nano Banana 生成图像

curl -X POST https://api.muapi.ai/api/v1/nano-banana \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A small glass greenhouse on a mossy hillside at sunrise","aspect_ratio":"1:1"}'

# Response: {"request_id":"REQUEST_ID"}

Send a prompt to a Nano Banana image endpoint.

2.使用Imagen 4生成图像

curl -X POST https://api.muapi.ai/api/v1/google-imagen4 \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A richly detailed glasshouse at sunrise, dew on tropical leaves","aspect_ratio":"16:9","num_images":1}'

# Response: {"request_id":"REQUEST_ID"}

向 Imagen 4 提交提示和宽高比。

3.使用Veo 3.1生成视频

呼叫 Veo 并提供提示和持续时间。

4. 使用 Gemini Omni 生成视频

curl -X POST https://api.muapi.ai/api/v1/gemini-omni-text-to-video \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A chef explains a recipe in a warm studio kitchen","resolution":"1080p","duration":8,"aspect_ratio":"16:9"}'

# Response: {"request_id":"REQUEST_ID"}

创建具有同步音频的视频。

5. 使用 Gemini TTS 生成语音

curl -X POST https://api.muapi.ai/api/v1/gemini-3-8-flash-tts \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"speakers":[{"speaker_id":"Speaker 1","voice_name":"Kore","accent":"Neutral","style":"Empathetic","pace":"Natural"}],"dialogue_turns":[{"speaker_id":"Speaker 1","text":"Welcome to the show."}]}'

# Response: {"request_id":"REQUEST_ID"}

提供结构化的演讲者和对话轮流。

6. 轮询已完成的输出

将返回的请求 ID 与共享结果端点一起使用。