文件 API

Gemini 可以同时处理各种类型的输入数据，包括文本、图片和音频。

本指南介绍了如何使用 Files API 处理媒体文件。对于音频文件、图片、视频、文档和其他受支持的文件类型，基本操作是相同的。

如需了解文件提示方面的指导，请参阅文件提示指南部分。

上传文件

您可以使用 Files API 上传媒体文件。当总请求大小（包括文件、文本提示、系统指令等）超过 100 MB 时，请务必使用 Files API。对于 PDF 文件，上限为 50 MB。

以下代码会上传文件，然后在对 interactions.create 的调用中使用该文件。

Python

from google import genai

client = genai.Client()

myfile = client.files.upload(file="path/to/sample.mp3")

interaction = client.interactions.create(
    model="gemini-3.6-flash",
    input=[
        {"type": "text", "text": "Describe this audio clip"},
        {"type": "audio", "uri": myfile.uri, "mime_type": myfile.mime_type}
    ]
)

print(interaction.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

async function main() {
  const myfile = await client.files.upload({
    file: "path/to/sample.mp3",
    config: { mime_type: "audio/mpeg" },
  });

  const interaction = await client.interactions.create({
    model: "gemini-3.6-flash",
    input: [
      { type: "text", text: "Describe this audio clip" },
      { type: "audio", uri: myfile.uri, mime_type: myfile.mimeType }
    ]
  });
  console.log(interaction.output_text);
}

await main();

Go

file, err := client.Files.UploadFromPath(ctx, "path/to/sample.mp3", nil)
if err != nil {
    log.Fatal(err)
}
defer client.Files.Delete(ctx, file.Name)

interaction, err := client.Interactions.Create(ctx, "gemini-3.6-flash", &genai.InteractionRequest{
    Input: []interface{}{
        genai.NewPartFromFile(*file),
        genai.NewPartFromText("Describe this audio clip"),
    },
}, nil)

if err != nil {
    log.Fatal(err)
}

// Print the model's text response
for _, step := range interaction.Steps {
    if step.Type == "model_output" {
        for _, part := range step.Content {
            if part.Type == "text" {
                fmt.Println(part.Text)
            }
        }
    }
}

REST

AUDIO_PATH="path/to/sample.mp3"
MIME_TYPE=$(file -b --mime-type "${AUDIO_PATH}")
NUM_BYTES=$(wc -c < "${AUDIO_PATH}")
DISPLAY_NAME=AUDIO

tmp_header_file=upload-header.tmp

# Initial resumable request defining metadata.
# The upload url is in the response headers dump them to a file.
curl "${BASE_URL}/upload/v1beta/files" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -D "${tmp_header_file}" \
  -H "X-Goog-Upload-Protocol: resumable" \
  -H "X-Goog-Upload-Command: start" \
  -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d