Понимание звука

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-3.8-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)

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-3.8-flash",
    input: [
        {type: "text", text: "Describe this audio clip"},
        {
            type: "audio",
            uri: uploadedFile.uri,
            mime_type: uploadedFile.mimeType
        }
    ]
});
console.log(interaction.output_text);

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AudioContent;
import com.google.genai.gaos.models.interactions.AudioContentMimeType;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;
import java.util.List;

Client client = new Client();

Content textContent = TextContent.builder().text("Provide a transcript and summary of this audio.").build();
Content audioContent =
    AudioContent.builder()
        .uri("gs://cloud-samples-data/generative-ai/audio/pixel.mp3")
        .mimeType(AudioContentMimeType.AUDIO_MP3)
        .build();

List<Content> contents = Arrays.asList(textContent, audioContent);

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.ofContent(contents))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

System.out.println(interaction.outputText().orElse(""));

# 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' \
  -d '{
    "model": "gemini-3.8-flash",
    "input": [
      {"type": "text", "text": "Describe this audio clip"},
      {
        "type": "audio",
        "uri": "YOUR_FILE_URI",
        "mime_type": "audio/mp3"
      }
    ]
  }'

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-3.8-flash",
    input=[
        {"type": "video", "uri": YOUTUBE_URL, "mime_type": "video/mp4"},
        {"type": "text", "text": prompt}
    ],
    response_format=response_schema,
)

print(interaction.output_text)

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"]