Gemini 3 Pro telah hadir. Coba gratis di Google AI Studio.

Halaman ini diterjemahkan oleh Cloud Translation API.

Pemahaman audio

Gemini dapat menganalisis dan memahami input audio serta menghasilkan respons teks untuk input tersebut, sehingga memungkinkan kasus penggunaan seperti berikut:

Mendeskripsikan, meringkas, atau menjawab pertanyaan tentang konten audio.
Memberikan transkripsi dan terjemahan audio (speech to text).
Mendeteksi dan melabeli pembicara yang berbeda (diarisasi pembicara).
Mendeteksi emosi dalam ucapan dan musik.
Menganalisis segmen audio tertentu, dan memberikan stempel waktu.

Saat ini, Gemini API tidak mendukung kasus penggunaan transkripsi real-time. Untuk interaksi suara dan video real-time, lihat Live API. Untuk model speech-to-text khusus dengan dukungan untuk transkripsi real-time, gunakan Google Cloud Speech-to-Text API.

Mentranskripsikan ucapan ke teks

Aplikasi contoh ini menunjukkan cara meminta Gemini API untuk mentranskripsikan, menerjemahkan, dan meringkas ucapan, termasuk stempel waktu, diarization penutur, dan deteksi emosi menggunakan output terstruktur.

Python

from google import genai
from google.genai import types

client = genai.Client()

YOUTUBE_URL = "https://www.youtube.com/watch?v=ku-N-eS1lgM"

def main():
  prompt = """
    Process the audio file and generate a detailed transcription.

    Requirements:
    1. Identify distinct speakers (e.g., Speaker 1, Speaker 2, or names if context allows).
    2. Provide accurate timestamps for each segment (Format: MM:SS).
    3. Detect the primary language of each segment.
    4. If the segment is in a language different than English, also provide the English translation.
    5. Identify the primary emotion of the speaker in this segment. You MUST choose exactly one of the following: Happy, Sad, Angry, Neutral.
    6. Provide a brief summary of the entire audio at the beginning.
  """

  response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[
      types.Content(
        parts=[
          types.Part(
            file_data=types.FileData(
              file_uri=YOUTUBE_URL
            )
          ),
          types.Part(
            text=prompt
          )
        ]
      )
    ],
    config=types.GenerateContentConfig(
      response_mime_type="application/json",
      response_schema=types.Schema(
        type=types.Type.OBJECT,
        properties={
          "summary": types.Schema(
            type=types.Type.STRING,
            description="A concise summary of the audio content.",
          ),
          "segments": types.Schema(
            type=types.Type.ARRAY,
            description="List of transcribed segments with speaker and timestamp.",
            items=types.Schema(
              type=types.Type.OBJECT,
              properties={
                "speaker": types.Schema(type=types.Type.STRING),
                "timestamp": types.Schema(type=types.Type.STRING),
                "content": types.Schema(type=types.Type.STRING),
                "language": types.Schema(type=types.Type.STRING),
                "language_code": types.Schema(type=types.Type.STRING),
                "translation": types.Schema(type=types.Type.STRING),
                "emotion": types.Schema(
                  type=types.Type.STRING,
                  enum=["happy", "sad", "angry", "neutral"]
                ),
              },
              required=["speaker", "timestamp", "content", "language", "language_code", "emotion"],
            ),
          ),
        },
        required=["summary", "segments"],
      ),
    ),
  )

  print(response.text)

if __name__ == "__main__":
  main()

JavaScript

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

const ai = new GoogleGenAI({});

const YOUTUBE_URL = "https://www.youtube.com/watch?v=ku-N-eS1lgM";

async function main() {
  const prompt = `
      Process the audio file and generate a detailed transcription.

      Requirements:
      1. Identify distinct speakers (e.g., Speaker 1, Speaker 2, or names if context allows).
      2. Provide accurate timestamps for each segment (Format: MM:SS).
      3. Detect the primary language of each segment.
      4. If the segment is in a language different than English, also provide the English translation.
      5. Identify the primary emotion of the speaker in this segment. You MUST choose exactly one of the following: Happy, Sad, Angry, Neutral.
      6. Provide a brief summary of the entire audio at the beginning.
    `;

  const Emotion = {
    Happy: 'happy',
    Sad: 'sad',
    Angry: 'angry',
    Neutral: 'neutral'
  };

  const response = await ai.models.generateContent({
    model: "gemini-2.5-flash",
    contents: {
      parts: [
        {
          fileData: {
            fileUri: YOUTUBE_URL,
          },
        },
        {
          text: prompt,
        },
      ],
    },
    config: {
      responseMimeType: "application/json",
      responseSchema: {
        type: Type.OBJECT,
        properties: {
          summary: {
            type: Type.STRING,
            description: "A concise summary of the audio content.",
          },
          segments: {
            type: Type.ARRAY,
            description: "List of transcribed segments with speaker and timestamp.",
            items: {
              type: Type.OBJECT,
              properties: {
                speaker: { type: Type.STRING },
                timestamp: { type: Type.STRING },
                content: { type: Type.STRING },
                language: { type: Type.STRING },
                language_code: { type: Type.STRING },
                translation: { type: Type.STRING },
                emotion: {
                  type: Type.STRING,
                  enum: Object.values(Emotion)
                },
              },
              required: ["speaker", "timestamp", "content", "language", "language_code", "emotion"],
            },
          },
        },
        required: ["summary", "segments"],
      },
    },
  });
  const json = JSON.parse(response.text);
  console.log(json);
}

await main();

REST

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [
        {
          "parts": [
            {
              "file_data": {
                "file_uri": "https://www.youtube.com/watch?v=ku-N-eS1lgM",
                "mime_type": "video/mp4"
              }
            },
            {
              "text": "Process the audio file and generate a detailed transcription.\n\nRequirements:\n1. Identify distinct speakers (e.g., Speaker 1, Speaker 2, or names if context allows).\n2. Provide accurate timestamps for each segment (Format: MM:SS).\n3. Detect the primary language of each segment.\n4. If the segment is in a language different than English, also provide the English translation.\n5. Identify the primary emotion of the speaker in this segment. You MUST choose exactly one of the following: Happy, Sad, Angry, Neutral.\n6. Provide a brief summary of the entire audio at the beginning."
            }
          ]
        }
      ],
      "generation_config": {
        "response_mime_type": "application/json",
        "response_schema": {
          "type": "OBJECT",
          "properties": {
            "summary": {
              "type": "STRING",
              "description": "A concise summary of the audio content."
            },
            "segments": {
              "type": "ARRAY",
              "description": "List of transcribed segments with speaker and timestamp.",
              "items": {
                "type": "OBJECT",
                "properties": {
                  "speaker": { "type": "STRING" },
                  "timestamp": { "type": "STRING" },
                  "content": { "type": "STRING" },
                  "language": { "type": "STRING" },
                  "language_code": { "type": "STRING" },
                  "translation": { "type": "STRING" },
                  "emotion": {
                    "type": "STRING",
                    "enum": ["happy", "sad", "angry", "neutral"]
                  }
                },
                "required": ["speaker", "timestamp", "content", "language", "language_code", "emotion"]
              }
            }
          },
          "required": ["summary", "segments"]
        }
      }
    }' 2> /dev/null > response.json

cat response.json
echo

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

Anda dapat meminta AI Studio Build untuk membuat aplikasi transkripsi seperti ini, hanya dengan mengklik satu tombol.

Aplikasi Gemini dengan transkripsi audio multibahasa

Input audio

Anda dapat memberikan data audio ke Gemini dengan cara berikut:

Upload file audio sebelum membuat permintaan ke generateContent.
Teruskan data audio inline dengan permintaan ke generateContent.

Mengupload file audio

Anda dapat menggunakan Files API untuk mengupload file audio. Selalu gunakan Files API jika ukuran total permintaan (termasuk file, perintah teks, petunjuk sistem, dll.) lebih besar dari 20 MB.

Kode berikut mengupload file audio, lalu menggunakan file tersebut dalam panggilan ke generateContent.

Python

from google import genai

client = genai.Client()

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

response = client.models.generate_content(
    model="gemini-2.5-flash", contents=["Describe this audio clip", myfile]
)

print(response.text)

JavaScript

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

const ai = new GoogleGenAI({});

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-2.5-flash",
    contents: createUserContent([
      createPartFromUri(myfile.uri, myfile.mimeType),
      "Describe this audio clip",
    ]),
  });
  console.log(response.text);
}

await main();

Go

package main

import (
  "context"
  "fmt"
  "os"
  "google.golang.org/genai"
)

func main() {
  ctx := context.Background()
  client, err := genai.NewClient(ctx, nil)
  if err != nil {
      log.Fatal(err)
  }

  localAudioPath := "/path/to/sample.mp3"
  uploadedFile, _ := client.Files.UploadFromPath(
      ctx,
      localAudioPath,
      nil,
  )

  parts := []*genai.Part{
      genai.NewPartFromText("Describe this audio clip"),
      genai.NewPartFromURI(uploadedFile.URI, uploadedFile.MIMEType),
  }
  contents := []*genai.Content{
      genai.NewContentFromParts(parts, genai.RoleUser),
  }

  result, _ := client.Models.GenerateContent(
      ctx,
      "gemini-2.5-flash",
      contents,
      nil,
  )

  fmt.Println(result.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 "https://generativelanguage.googleapis.com/upload/v1beta/files" \
  -H "x-goog-api-key: $GEMINI_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-2.5-flash:generateContent" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "Describe this audio clip"},
          {"file_data":{"mime_type": "${MIME_TYPE}", "file_uri": '$file_uri'}}]
        }]
      }' 2> /dev/null > response.json

cat response.json
echo

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

Untuk mempelajari lebih lanjut cara menggunakan file media, lihat Files API.

Meneruskan data audio secara inline

Daripada mengupload file audio, Anda dapat meneruskan data audio inline dalam permintaan ke generateContent:

Python

from google import genai
from google.genai import types

with open('path/to/small-sample.mp3', 'rb') as f:
    audio_bytes = f.read()

client = genai.Client()
response = client.models.generate_content(
  model='gemini-2.5-flash',
  contents=[
    'Describe this audio clip',
    types.Part.from_bytes(
      data=audio_bytes,
      mime_type='audio/mp3',
    )
  ]
)

print(response.text)

JavaScript

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

const ai = new GoogleGenAI({});
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-2.5-flash",
  contents: contents,
});
console.log(response.text);

Go

package main

import (
  "context"
  "fmt"
  "os"
  "google.golang.org/genai"
)

func main() {
  ctx := context.Background()
  client, err := genai.NewClient(ctx, nil)
  if err != nil {
      log.Fatal(err)
  }

  audioBytes, _ := os.ReadFile("/path/to/small-sample.mp3")

  parts := []*genai.Part{
      genai.NewPartFromText("Describe this audio clip"),
    &genai.Part{
      InlineData: &genai.Blob{
        MIMEType: "audio/mp3",
        Data:     audioBytes,
      },
    },
  }
  contents := []*genai.Content{
      genai.NewContentFromParts(parts, genai.RoleUser),
  }

  result, _ := client.Models.GenerateContent(
      ctx,
      "gemini-2.5-flash",
      contents,
      nil,
  )

  fmt.Println(result.Text())
}

Beberapa hal yang perlu diingat tentang data audio inline:

Ukuran permintaan maksimum adalah 20 MB, yang mencakup perintah teks, petunjuk sistem, dan file yang disediakan secara inline. Jika ukuran file Anda akan membuat total ukuran permintaan melebihi 20 MB, maka gunakan Files API untuk mengupload file audio untuk digunakan dalam permintaan.
Jika Anda menggunakan sampel audio beberapa kali, akan lebih efisien untuk mengupload file audio.

Mendapatkan transkrip

Untuk mendapatkan transkrip data audio, cukup minta di perintah:

Python

from google import genai

client = genai.Client()
myfile = client.files.upload(file='path/to/sample.mp3')
prompt = 'Generate a transcript of the speech.'

response = client.models.generate_content(
  model='gemini-2.5-flash',
  contents=[prompt, myfile]
)

print(response.text)

JavaScript

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

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

const result = await ai.models.generateContent({
  model: "gemini-2.5-flash",
  contents: createUserContent([
    createPartFromUri(myfile.uri, myfile.mimeType),
    "Generate a transcript of the speech.",
  ]),
});
console.log("result.text=", result.text);

Go

package main

import (
  "context"
  "fmt"
  "os"
  "google.golang.org/genai"
)

func main() {
  ctx := context.Background()
  client, err := genai.NewClient(ctx, nil)
  if err != nil {
      log.Fatal(err)
  }

  localAudioPath := "/path/to/sample.mp3"
  uploadedFile, _ := client.Files.UploadFromPath(
      ctx,
      localAudioPath,
      nil,
  )

  parts := []*genai.Part{
      genai.NewPartFromText("Generate a transcript of the speech."),
      genai.NewPartFromURI(uploadedFile.URI, uploadedFile.MIMEType),
  }
  contents := []*genai.Content{
      genai.NewContentFromParts(parts, genai.RoleUser),
  }

  result, _ := client.Models.GenerateContent(
      ctx,
      "gemini-2.5-flash",
      contents,
      nil,
  )

  fmt.Println(result.Text())
}

Merujuk pada stempel waktu

Anda dapat merujuk ke bagian tertentu dari file audio menggunakan stempel waktu dalam bentuk MM:SS. Misalnya, perintah berikut meminta transkrip yang

Dimulai pada 2 menit 30 detik dari awal file.
Berakhir pada 3 menit 29 detik dari awal file.

Python

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

JavaScript

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

Go

package main

import (
  "context"
  "fmt"
  "os"
  "google.golang.org/genai"
)

func main() {
  ctx := context.Background()
  client, err := genai.NewClient(ctx, nil)
  if err != nil {
      log.Fatal(err)
  }

  localAudioPath := "/path/to/sample.mp3"
  uploadedFile, _ := client.Files.UploadFromPath(
      ctx,
      localAudioPath,
      nil,
  )

  parts := []*genai.Part{
      genai.NewPartFromText("Provide a transcript of the speech " +
                            "between the timestamps 02:30 and 03:29."),
      genai.NewPartFromURI(uploadedFile.URI, uploadedFile.MIMEType),
  }
  contents := []*genai.Content{
      genai.NewContentFromParts(parts, genai.RoleUser),
  }

  result, _ := client.Models.GenerateContent(
      ctx,
      "gemini-2.5-flash",
      contents,
      nil,
  )

  fmt.Println(result.Text())
}

Menjumlahkan token

Panggil metode countTokens untuk mendapatkan jumlah token dalam file audio. Contoh:

Python

from google import genai

client = genai.Client()
response = client.models.count_tokens(
  model='gemini-2.5-flash',
  contents=[myfile]
)

print(response)

JavaScript

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

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

const countTokensResponse = await ai.models.countTokens({
  model: "gemini-2.5-flash",
  contents: createUserContent([
    createPartFromUri(myfile.uri, myfile.mimeType),
  ]),
});
console.log(countTokensResponse.totalTokens);

Go

package main

import (
  "context"
  "fmt"
  "os"
  "google.golang.org/genai"
)

func main() {
  ctx := context.Background()
  client, err := genai.NewClient(ctx, nil)
  if err != nil {
      log.Fatal(err)
  }

  localAudioPath := "/path/to/sample.mp3"
  uploadedFile, _ := client.Files.UploadFromPath(
      ctx,
      localAudioPath,
      nil,
  )

  parts := []*genai.Part{
      genai.NewPartFromURI(uploadedFile.URI, uploadedFile.MIMEType),
  }
  contents := []*genai.Content{
      genai.NewContentFromParts(parts, genai.RoleUser),
  }

  tokens, _ := client.Models.CountTokens(
      ctx,
      "gemini-2.5-flash",
      contents,
      nil,
  )

  fmt.Printf("File %s is %d tokens\n", localAudioPath, tokens.TotalTokens)
}

Format audio yang didukung

Gemini mendukung jenis MIME format audio berikut:

WAV - audio/wav
MP3 - audio/mp3
AIFF - audio/aiff
AAC - audio/aac
OGG Vorbis - audio/ogg
FLAC - audio/flac

Detail teknis tentang audio

Gemini merepresentasikan setiap detik audio sebagai 32 token; misalnya, satu menit audio direpresentasikan sebagai 1.920 token.
Gemini dapat "memahami" komponen non-ucapan, seperti kicauan burung atau sirene.
Durasi maksimum data audio yang didukung dalam satu perintah adalah 9,5 jam. Gemini tidak membatasi jumlah file audio dalam satu perintah; namun, total durasi gabungan semua file audio dalam satu perintah tidak boleh melebihi 9,5 jam.
Gemini melakukan downsampling file audio ke resolusi data 16 Kbps.
Jika sumber audio berisi beberapa saluran, Gemini akan menggabungkan saluran tersebut menjadi satu saluran.

Langkah berikutnya

Panduan ini menunjukkan cara membuat teks sebagai respons terhadap data audio. Untuk mempelajari lebih lanjut, lihat referensi berikut:

Strategi perintah file: Gemini API mendukung perintah dengan data teks, gambar, audio, dan video, yang juga dikenal sebagai perintah multimodal.
Petunjuk sistem: Petunjuk sistem memungkinkan Anda mengarahkan perilaku model berdasarkan kebutuhan dan kasus penggunaan spesifik Anda.
Panduan keamanan: Terkadang model AI generatif menghasilkan output yang tidak terduga, seperti output yang tidak akurat, bias, atau menyinggung. Pemrosesan pasca-pembuatan dan evaluasi manusia sangat penting untuk membatasi risiko bahaya dari output tersebut.