Compreensão de áudio (original) (raw)

Ir para o conteúdo principal

O Gemini pode analisar e entender entradas de áudio e gerar respostas de texto para elas, permitindo casos de uso como os seguintes:

No momento, a API Gemini não oferece suporte a casos de uso de transcrição em tempo real. Para interações de voz e vídeo em tempo real, consulte a API Live. Para modelos dedicados de conversão de voz em texto com suporte à transcrição em tempo real, use a API Cloud Speech-to-Text do Google.

Transcrever voz em texto

Este aplicativo de exemplo mostra como solicitar à API Gemini que transcreva, traduza e resuma falas, incluindo carimbos de data/hora, diarização de falantes e detecção de emoções usandosaídas estruturadas.

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

Você pode pedir para o AI Studio Build criar um app de transcrição como este com apenas um clique.

Um app Gemini de transcrição de áudio multilíngue

Áudio de entrada

Você pode fornecer dados de áudio ao Gemini das seguintes maneiras:

Fazer upload de um arquivo de áudio

Use a API Files para fazer upload de um arquivo de áudio. Sempre use a API Files quando o tamanho total da solicitação (incluindo arquivos, comando de texto, instruções do sistema etc.) for maior que 20 MB.

O código a seguir faz upload de um arquivo de áudio e o usa em uma chamada paragenerateContent.

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

Para saber mais sobre como trabalhar com arquivos de mídia, consulte aAPI Files.

Transmitir dados de áudio inline

Em vez de fazer upload de um arquivo de áudio, você pode transmitir dados de áudio inline na solicitação para 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())
}

Alguns lembretes sobre dados de áudio inline:

Acessar uma transcrição

Para receber uma transcrição de dados de áudio, basta pedir no comando:

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())
}

Consulte os carimbos de data/hora

É possível se referir a seções específicas de um arquivo de áudio usando carimbos de data/hora no formatoMM:SS. Por exemplo, o comando a seguir solicita uma transcrição que

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())
}

Contar tokens

Chame o método countTokens para receber uma contagem do número de tokens em um arquivo de áudio. Exemplo:

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)
}

Formatos de áudio compatíveis

O Gemini é compatível com os seguintes tipos MIME de formato de áudio:

Detalhes técnicos sobre áudio

A seguir

Este guia mostra como gerar texto em resposta a dados de áudio. Para saber mais, consulte os seguintes recursos:

Exceto em caso de indicação contrária, o conteúdo desta página é licenciado de acordo com a Licença de atribuição 4.0 do Creative Commons, e as amostras de código são licenciadas de acordo com a Licença Apache 2.0. Para mais detalhes, consulte as políticas do site do Google Developers. Java é uma marca registrada da Oracle e/ou afiliadas.

Última atualização 2025-12-03 UTC.