Comprensión de audio

Gemini puede analizar la entrada de audio y generar respuestas de texto.

Python

from google import genai
import base64

client = genai.Client()

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

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input=[
        {"type": "text", "text": "Describe this audio clip"},
        {
            "type": "audio",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        }
    ]
)
print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

const uploadedFile = await client.files.upload({
    file: "path/to/sample.mp3",
    config: { mime_type: "audio/mp3" }
});

const interaction = await client.interactions.create({
    model: "gemini-3.5-flash",
    input: [
        {type: "text", text: "Describe this audio clip"},
        {
            type: "audio",
            uri: uploadedFile.uri,
            mime_type: uploadedFile.mimeType
        }
    ]
});
console.log(interaction.output_text);

REST

# First upload the file, then use the URI:
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3.5-flash",
    "input": [
      {"type": "text", "text": "Describe this audio clip"},
      {
        "type": "audio",
        "uri": "YOUR_FILE_URI",
        "mime_type": "audio/mp3"
      }
    ]
  }'

Descripción general

Gemini puede analizar y comprender la entrada de audio, y generar respuestas de texto, lo que permite casos de uso como los siguientes:

  • Describir, resumir o responder preguntas sobre el contenido de audio
  • Transcripción y traducción (voz a texto)
  • Identificación de interlocutores (identifica a los diferentes interlocutores)
  • Detección de emociones en la voz y la música
  • Cómo analizar segmentos específicos con marcas de tiempo

Para interacciones de voz y video en tiempo real, consulta la API de Live. Para los modelos de voz a texto dedicados que admiten la transcripción en tiempo real, usa la API de Google Cloud Speech-to-Text.

Transcribe voz a texto

En este ejemplo, se muestra cómo transcribir, traducir y resumir el habla con marcas de tiempo, identificación del orador y detección de emociones con salidas estructuradas.

Python

from google import genai

client = genai.Client()

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

prompt = """
  Process the audio file and generate a detailed transcription.

  Requirements:
  1. Identify distinct speakers (e.g., Speaker 1, Speaker 2).
  2. Provide accurate timestamps for each segment (Format: MM:SS).
  3. Detect the primary language of each segment.
  4. If not English, provide the English translation.
  5. Identify the primary emotion: Happy, Sad, Angry, or Neutral.
  6. Provide a brief summary at the beginning.
"""

response_schema = {
    "type": "object",
    "properties": {
        "summary": {"type": "string"},
        "segments": {
            "type": "array",
            "items": {
                "type": "object",
                "properties": {
                    "speaker": {"type": "string"},
                    "timestamp": {"type": "string"},
                    "content": {"type": "string"},
                    "language": {"type": "string"},
                    "emotion": {
                        "type": "string",
                        "enum": ["happy", "sad", "angry", "neutral"]
                    }
                },
                "required": ["speaker", "timestamp", "content", "emotion"]
            }
        }
    },
    "required": ["summary", "segments"]
}

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input=[
        {"type": "video", "uri": YOUTUBE_URL, "mime_type": "video/mp4"},
        {"type": "text", "text": prompt}
    ],
    response_format=response_schema,
)

print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

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

const prompt = `
  Process the audio file and generate a detailed transcription.

  Requirements:
  1. Identify distinct speakers (e.g., Speaker 1, Speaker 2).
  2. Provide accurate timestamps for each segment (Format: MM:SS).
  3. Detect the primary language of each segment.
  4. If not English, provide the English translation.
  5. Identify the primary emotion: Happy, Sad, Angry, or Neutral.
  6. Provide a brief summary at the beginning.
`;

const responseSchema = {
    type: "object",
    properties: {
        summary: { type: "string" },
        segments: {
            type: "array",
            items: {
                type: "object",
                properties: {
                    speaker: { type: "string" },
                    timestamp: { type: "string" },
                    content: { type: "string" },
                    language: { type: "string" },
                    emotion: {
                        type: "string",
                        enum: ["happy", "sad", "angry", "neutral"]
                    }
                },
                required: ["speaker", "timestamp", "content", "emotion"]
            }
        }
    },
    required: ["summary", "segments"]
};

const interaction = await client.interactions.create({
    model: "gemini-3.5-flash",
    input: [
        { type: "video", uri: YOUTUBE_URL, mime_type: "video/mp4" },
        { type: "text", text: prompt }
    ],
    response_format: responseSchema,
});

console.log(JSON.parse(interaction.output_text));

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3.5-flash",
    "input": [
      {
        "type": "video",
        "uri": "https://www.youtube.com/watch?v=ku-N-eS1lgM",
        "mime_type": "video/mp4"
      },
      {
        "type": "text",
        "text": "Transcribe with speaker diarization and emotion detection."
      }
    ],
    "response_format": {
        "type": "object",
        "properties": {
          "summary": {"type": "string"},
          "segments": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "speaker": {"type": "string"},
                "timestamp": {"type": "string"},
                "content": {"type": "string"},
                "emotion": {"type": "string", "enum": ["happy", "sad", "angry", "neutral"]}
              }
            }
          }
        }
      }
  }'

Una app de Gemini para la transcripción de audio en varios idiomas

Audio de entrada

Puedes proporcionar datos de audio de las siguientes maneras:

Sube un archivo de audio

Usa la API de Files para archivos de más de 20 MB.

Python

from google import genai

client = genai.Client()

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

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input=[
        {"type": "text", "text": "Describe this audio clip"},
        {
            "type": "audio",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        }
    ]
)
print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

const uploadedFile = await client.files.upload({
    file: "path/to/sample.mp3",
    config: { mimeType: "audio/mp3" }
});

const interaction = await client.interactions.create({
    model: "gemini-3.5-flash",
    input: [
        {type: "text", text: "Describe this audio clip"},
        {
            type: "audio",
            uri: uploadedFile.uri,
            mime_type: uploadedFile.mimeType
        }
    ]
});
console.log(interaction.output_text);

REST

# First upload the file using the Files API, then use the URI:
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3.5-flash",
    "input": [
      {"type": "text", "text": "Describe this audio clip"},
      {
        "type": "audio",
        "uri": "YOUR_FILE_URI",
        "mime_type": "audio/mp3"
      }
    ]
  }'

Cómo pasar datos de audio intercalados

Para archivos de audio pequeños con un tamaño total de la solicitud inferior a 20 MB, haz lo siguiente:

Python

from google import genai
import base64

client = genai.Client()

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

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input=[
        {"type": "text", "text": "Describe this audio clip"},
        {
            "type": "audio",
            "data": base64.b64encode(audio_bytes).decode('utf-8'),
            "mime_type": "audio/mp3"
        }
    ]
)
print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

const audioData = fs.readFileSync("path/to/small-sample.mp3", {
    encoding: "base64"
});

const interaction = await client.interactions.create({
    model: "gemini-3.5-flash",
    input: [
        {type: "text", text: "Describe this audio clip"},
        {
            type: "audio",
            data: audioData,
            mime_type: "audio/mp3"
        }
    ]
});
console.log(interaction.output_text);

REST

AUDIO_PATH="path/to/sample.mp3"

if [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
  B64FLAGS="--input"
else
  B64FLAGS="-w0"
fi

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3.5-flash",
    "input": [
      {"type": "text", "text": "Describe this audio clip"},
      {
        "type": "audio",
        "data": "'$(base64 $B64FLAGS $AUDIO_PATH)'",
        "mime_type": "audio/mp3"
      }
    ]
  }'

Notas sobre los datos de audio intercalados: * El tamaño máximo de la solicitud es de 20 MB en total (incluidas las instrucciones y todos los archivos). * Para reutilizar el audio, sube el archivo.

Cómo obtener una transcripción

Para obtener una transcripción, pídesela en la instrucción:

Python

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input=[
        {"type": "text", "text": "Generate a transcript of the speech."},
        {
            "type": "audio",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        }
    ]
)
print(interaction.output_text)

JavaScript

const interaction = await client.interactions.create({
    model: "gemini-3.5-flash",
    input: [
        { type: "text", text: "Generate a transcript of the speech." },
        {
            type: "audio",
            uri: uploadedFile.uri,
            mime_type: uploadedFile.mimeType
        }
    ]
});
console.log(interaction.output_text);

Consulta las marcas de tiempo

Usa el formato MM:SS para hacer referencia a secciones específicas:

Python

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input=[
        {"type": "text", "text": "Provide a transcript from 02:30 to 03:29."},
        {
            "type": "audio",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        }
    ]
)

JavaScript

const interaction = await client.interactions.create({
    model: "gemini-3.5-flash",
    input: [
        { type: "text", text: "Provide a transcript from 02:30 to 03:29." },
        { type: "audio", uri: uploadedFile.uri, mime_type: "audio/mp3" }
    ]
});

Cuenta tokens

Para contar los tokens en un archivo de audio, haz lo siguiente:

Python

response = client.models.count_tokens(
    model="gemini-3.5-flash",
    contents=[uploaded_file]
)
print(response)

JavaScript

const response = await client.models.countTokens({
    model: "gemini-3.5-flash",
    contents: [
        { fileData: { fileUri: uploadedFile.uri, mimeType: uploadedFile.mimeType } }
    ]
});
console.log(response.totalTokens);

Formatos de audio compatibles

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

Detalles técnicos sobre el audio

  • Tokens: 32 tokens por segundo de audio (1 minuto = 1,920 tokens)
  • Sonidos no verbales: Gemini comprende los sonidos no verbales (canto de pájaros, sirenas, etc.).
  • Longitud máxima: 9.5 horas de audio por instrucción
  • Resolución: Se redujo la muestra a 16 Kbps.
  • Canales: Audio multicanal combinado en un solo canal

¿Qué sigue?