Gemini 3 Pro 隆重登場！在 Google AI Studio 中免費試用。

本頁面由 Cloud Translation API 翻譯而成。

音訊理解

Gemini 可以分析及理解音訊輸入內容，並生成文字回覆，適用於以下應用情境：

描述音訊內容、生成摘要或回答相關問題。
提供音訊的轉錄稿和翻譯 (語音轉文字)。
偵測不同的說話者並加上標籤 (說話者分段標記)。
偵測語音和音樂中的情緒。
分析音訊的特定片段，並提供時間戳記。

Gemini API 目前不支援即時轉錄功能。如需即時語音和視訊互動，請參閱 Live API。如要使用支援即時轉錄的專用語音轉文字模型，請使用 Google Cloud Speech-to-Text API。

將語音轉錄成文字

這個範例應用程式會說明如何提示 Gemini API 轉錄、翻譯及摘要語音內容，包括時間戳記、說話者區分和情緒偵測，並使用結構化輸出。

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

只要按一下按鈕，就能提示 AI Studio Build 建立像這樣的轉錄應用程式。

支援多種語言的語音轉錄 Gemini 應用程式

輸入音訊

你可以透過下列方式向 Gemini 提供音訊資料：

請先上傳音訊檔案，再向 generateContent 提出要求。
透過要求將內嵌音訊資料傳遞至 generateContent。

上傳音訊檔案

您可以使用 Files API 上傳音訊檔。如果要求總大小 (包括檔案、文字提示、系統指令等) 超過 20 MB，請一律使用 Files API。

下列程式碼會上傳音訊檔案，然後在呼叫 generateContent 時使用該檔案。

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

如要進一步瞭解如何處理媒體檔案，請參閱 Files API。

內嵌傳遞音訊資料

您可以將內嵌音訊資料傳遞至 generateContent 的要求，不必上傳音訊檔案：

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())
}

使用內嵌音訊資料時，請注意下列事項：

要求大小上限為 20 MB，包括文字提示、系統指令和內嵌提供的檔案。如果檔案大小會導致要求總大小超過 20 MB，請使用 Files API 上傳音訊檔案，以供要求使用。
如果多次使用音訊樣本，建議上傳音訊檔案，這樣效率更高。

取得轉錄稿

如要取得音訊資料的轉錄稿，只要在提示中提出要求即可：

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())
}

參閱時間戳記

你可以使用 MM:SS 格式的時間戳記，參照音訊檔案的特定部分。舉例來說，下列提示會要求轉錄稿

從檔案開頭算起，2 分 30 秒處開始。
從檔案開頭算起，結束時間為 3 分 29 秒。

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())
}

計算詞元數

呼叫 countTokens 方法，即可取得音訊檔案中的權杖數量。例如：

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)
}

支援的音訊格式

Gemini 支援下列音訊格式 MIME 類型：

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

音訊技術詳細資料

Gemini 會將每秒音訊表示為 32 個權杖；舉例來說，一分鐘的音訊會表示為 1,920 個權杖。
Gemini 可以「瞭解」非語音成分，例如鳥鳴或警報聲。
單一提示支援的音訊資料長度上限為 9.5 小時。 Gemini 不會限制單一提示中的音訊檔案數量，但單一提示中所有音訊檔案的總長度不得超過 9.5 小時。
Gemini 會將音訊檔案降採樣至 16 Kbps 的資料解析度。
如果音訊來源包含多個聲道，Gemini 會將這些聲道合併為單一聲道。

後續步驟

本指南說明如何產生回應音訊資料的文字。如要瞭解詳情，請參閱下列資源：

檔案提示策略：Gemini API 支援使用文字、圖片、音訊和影片資料提示，也就是多模態提示。
系統指令：系統指令可根據特定需求和用途，引導模型行為。
安全指引：有時生成式 AI 模型會產生出乎意料的輸出內容，例如不準確、有偏見或令人反感的內容。後續處理和人工評估是不可或缺的環節，有助於降低這類輸出內容造成危害的風險。