การทำความเข้าใจเสียง

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-flash-preview",
    input=[
        {"type": "text", "text": "Describe this audio clip"},
        {
            "type": "audio",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        }
    ]
)
print(interaction.steps[-1].content[0].text)

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-flash-preview",
    input: [
        {type: "text", text: "Describe this audio clip"},
        {
            type: "audio",
            uri: uploadedFile.uri,
            mimeType: uploadedFile.mimeType
        }
    ]
});
console.log(interaction.steps.at(-1).content[0].text);

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

print(interaction.steps[-1].content[0].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"]
            }
        }
    },
    required: ["summary", "segments"]
};

const interaction = await client.interactions.create({
    model: "gemini-3-flash-preview",
    input: [
        { type: "uri", uri: YOUTUBE_URL, mimeType: "video/mp4" },
        { type: "text", text: prompt }
    ],
    response_format: responseSchema,
});

console.log(JSON.parse(interaction.steps.at(-1).content[0].text));

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-flash-preview",
    "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"]}
              }
            }
          }
        }
      }
  }'

from google import genai

client = genai.Client()

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

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "Describe this audio clip"},
        {
            "type": "audio",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        }
    ]
)
print(interaction.steps[-1].content[0].text)

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-flash-preview",
    input: [
        {type: "text", text: "Describe this audio clip"},
        {
            type: "audio",
            uri: uploadedFile.uri,
            mimeType: uploadedFile.mimeType
        }
    ]
});
console.log(interaction.steps.at(-1).content[0].text);

# 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' \
  -d '{
    "model": "gemini-3-flash-preview",
    "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()

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

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "Describe this audio clip"},
        {
            "type": "audio",
            "data": base64.b64encode(audio_bytes).decode('utf-8'),
            "mime_type": "audio/mp3"
        }
    ]
)
print(interaction.steps[-1].content[0].text)

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-flash-preview",
    input: [
        {type: "text", text: "Describe this audio clip"},
        {
            type: "audio",
            data: audioData,
            mimeType: "audio/mp3"
        }
    ]
});
console.log(interaction.steps.at(-1).content[0].text);

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: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": [
      {"type": "text", "text": "Describe this audio clip"},
      {
        "type": "audio",
        "data": "'$(base64 $B64FLAGS $AUDIO_PATH)'",
        "mime_type": "audio/mp3"
      }
    ]
  }'

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "Generate a transcript of the speech."},
        {
            "type": "audio",
            "uri": uploaded_file.uri,
            "mime_type": "audio/mp3"
        }
    ]
)
print(interaction.steps[-1].content[0].text)

const interaction = await client.interactions.create({
    model: "gemini-3-flash-preview",
    input: [
        { type: "text", text: "Generate a transcript of the speech." },
        {
            type: "audio",
            uri: uploadedFile.uri,
            mime_type: uploadedFile.mimeType
        }
    ]
});
console.log(interaction.steps.at(-1).content[0].text);

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "Provide a transcript from 02:30 to 03:29."},
        {
            "type": "audio",
            "uri": uploaded_file.uri,
            "mime_type": "audio/mp3"
        }
    ]
)

const interaction = await client.interactions.create({
    model: "gemini-3-flash-preview",
    input: [
        { type: "text", text: "Provide a transcript from 02:30 to 03:29." },
        { type: "audio", uri: uploadedFile.uri, mime_type: "audio/mp3" }
    ]
});

response = client.models.count_tokens(
    model='gemini-3-flash-preview',
    input=[
        {
            "type": "audio",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        }
    ]
)
print(response)

const response = await client.models.countTokens({
    model: "gemini-3-flash-preview",
    input: [
        {
            type: "audio",
            uri: uploadedFile.uri,
            mime_type: uploadedFile.mimeType
        }
    ]
});
console.log(response.totalTokens);