ความเข้าใจเกี่ยวกับเสียง

import {
  GoogleGenAI,
  createUserContent,
  createPartFromUri,
} from "@google/genai";

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });

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

  const response = await ai.models.generateContent({
    model: "gemini-2.0-flash",
    contents: createUserContent([
      createPartFromUri(myfile.uri, myfile.mimeType),
      "Describe this audio clip",
    ]),
  });
  console.log(response.text);
}

await main();

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

model := client.GenerativeModel("gemini-2.0-flash")
resp, err := model.GenerateContent(ctx,
    genai.FileData{URI: file.URI},
    genai.Text("Describe this audio clip"))
if err != nil {
    log.Fatal(err)
}

printResponse(resp)

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 "https://generativelanguage.googleapis.com/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
  -D upload-header.tmp \
  -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 generate content using that file
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "Describe this audio clip"},
          {"file_data":{"mime_type": "${MIME_TYPE}", "file_uri": '$file_uri'}}]
        }]
      }' 2> /dev/null > response.json

cat response.json
echo

jq ".candidates[].content.parts[].text" response.json

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });
const base64AudioFile = fs.readFileSync("path/to/small-sample.mp3", {
  encoding: "base64",
});

const contents = [
  { text: "Please summarize the audio." },
  {
    inlineData: {
      mimeType: "audio/mp3",
      data: base64AudioFile,
    },
  },
];

const response = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: contents,
});
console.log(response.text);

// Initialize a Gemini model appropriate for your use case.
model := client.GenerativeModel("gemini-2.0-flash")

bytes, err := os.ReadFile("path/to/small-sample.mp3")
if err != nil {
  log.Fatal(err)
}

prompt := []genai.Part{
  genai.Blob{MIMEType: "audio/mp3", Data: bytes},
  genai.Text("Please summarize the audio."),
}

// Generate content using the prompt.
resp, err := model.GenerateContent(ctx, prompt...)
if err != nil {
  log.Fatal(err)
}

// Handle the response of generated text
for _, c := range resp.Candidates {
  if c.Content != nil {
    fmt.Println(*c.Content)
  }
}

import {
  GoogleGenAI,
  createUserContent,
  createPartFromUri,
} from "@google/genai";

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });
const myfile = await ai.files.upload({
  file: "path/to/sample.mp3",
  config: { mimeType: "audio/mpeg" },
});

const result = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: createUserContent([
    createPartFromUri(myfile.uri, myfile.mimeType),
    "Generate a transcript of the speech.",
  ]),
});
console.log("result.text=", result.text);

// Initialize a Gemini model appropriate for your use case.
model := client.GenerativeModel("gemini-2.0-flash")

// Create a prompt using text and the URI reference for the uploaded file.
prompt := []genai.Part{
  genai.FileData{URI: sampleAudio.URI},
  genai.Text("Generate a transcript of the speech."),
}

// Generate content using the prompt.
resp, err := model.GenerateContent(ctx, prompt...)
if err != nil {
  log.Fatal(err)
}

// Handle the response of generated text
for _, c := range resp.Candidates {
  if c.Content != nil {
    fmt.Println(*c.Content)
  }
}

// Create a prompt containing timestamps.
const prompt = "Provide a transcript of the speech from 02:30 to 03:29."

// Create a prompt containing timestamps.
prompt := []genai.Part{
    genai.FileData{URI: sampleAudio.URI},
    genai.Text("Provide a transcript of the speech from 02:30 to 03:29."),
}

import {
  GoogleGenAI,
  createUserContent,
  createPartFromUri,
} from "@google/genai";

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });
const myfile = await ai.files.upload({
  file: "path/to/sample.mp3",
  config: { mimeType: "audio/mpeg" },
});

const countTokensResponse = await ai.models.countTokens({
  model: "gemini-2.0-flash",
  contents: createUserContent([
    createPartFromUri(myfile.uri, myfile.mimeType),
  ]),
});
console.log(countTokensResponse.totalTokens);

tokens, err := model.CountTokens(ctx, genai.FileData{URI: sampleAudio.URI})
if err != nil {
    log.Fatal(err)
}
fmt.Printf("File %s is %d tokens", sampleAudio.DisplayName, tokens.TotalTokens)