API Files

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)

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();

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)
            }
        }
    }
}

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" " -f2 | tr -d "\r")
rm "${tmp_header_file}"

# Upload the actual bytes.
curl "${upload_url}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${AUDIO_PATH}" 2> /dev/null > file_info.json

file_uri=$(jq ".file.uri" file_info.json)
echo file_uri=$file_uri

# Now create an interaction using the Interactions API
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
      "model": "gemini-3.6-flash",
      "input": [
        {"type": "text", "text": "Describe this audio clip"},
        {"type": "audio", "uri": '$file_uri', "mime_type": "'${MIME_TYPE}'"}
      ]
    }' 2> /dev/null > response.json

cat response.json
echo

jq ".outputs[] | select(.type == \"text\") | .text" response.json

from google import genai

client = genai.Client()

myfile = client.files.upload(file='path/to/sample.mp3')
file_name = myfile.name
myfile = client.files.get(name=file_name)
print(