> ## AI Agent Context
> Get the complete documentation index at: https://aistudio.google.com/docs/llms.txt
> Use this file to discover all available pages.
> For the full documentation in a single file, fetch: https://aistudio.google.com/docs/llms-full.txt

# Audio understanding

Gemini can analyze audio input and generate text responses.

{% tabs %}
  {% tab label="Python" %}
  ```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-3.8-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)
  ```

  {% /tab %}

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

  {% /tab %}

  {% tab label="Java" %}
  ```java
  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 com.google.genai.types.File;
  import com.google.genai.types.UploadFileConfig;
  import java.util.Arrays;
  import java.util.List;
  
  Client client = new Client();
  
  File uploadedFile =
      client.files.upload(
          "path/to/sample.mp3", UploadFileConfig.builder().mimeType("audio/mp3").build());
  
  Content textContent = TextContent.builder().text("Describe this audio clip").build();
  Content audioContent =
      AudioContent.builder()
          .uri(uploadedFile.uri().get())
          .mimeType(AudioContentMimeType.of(uploadedFile.mimeType().get()))
          .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(""));
  ```

  {% /tab %}

  {% tab label="Go" %}
  ```go
  package main
  
  import (
      "context"
      "fmt"
      "log"
  
      "google.golang.org/genai"
      "google.golang.org/genai/interactions/models/interactions"
      "google.golang.org/genai/interactions/models/operations"
  )
  
  func main() {
      ctx := context.Background()
      client, err := genai.NewClient(ctx, nil)
      if err != nil {
          log.Fatal(err)
      }
  
      uploadedFile, err := client.Files.UploadFromPath(ctx, "path/to/sample.mp3", &genai.UploadFileConfig{
          MIMEType: "audio/mp3",
      })
      if err != nil {
          log.Fatal(err)
      }
  
      contents := []interactions.Content{
          interactions.NewContent(interactions.TextContent{
              Text: "Describe this audio clip",
          }),
          interactions.NewContent(interactions.AudioContent{
              URI:      genai.Ptr(uploadedFile.URI),
              MimeType: interactions.AudioContentMimeType(uploadedFile.MIMEType).ToPointer(),
          }),
      }
  
      res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
          Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
              Model: interactions.Model("gemini-3.8-flash"),
              Input: interactions.NewInteractionsInput(contents),
          }),
      })
      if err != nil {
          log.Fatal(err)
      }
  
      if res.Interaction.OutputText != nil {
          fmt.Println(*res.Interaction.OutputText)
      }
  }
  ```

  {% /tab %}

  {% tab label="REST" %}
  ```shell
  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-3.8-flash",
      "input": [
        {"type": "text", "text": "Describe this audio clip"},
        {
          "type": "audio",
          "uri": "YOUR_FILE_URI",
          "mime_type": "audio/mp3"
        }
      ]
    }'
  ```

  {% /tab %}

{% /tabs %}

## Overview  {% id="overview" %}

Gemini can analyze and understand audio input and generate text responses,
enabling use cases like:

* Describe, summarize, or answer questions about audio content
* Transcription and translation (speech to text)
* Speaker diarization (identifying different speakers)
* Emotion detection in speech and music
* Analyzing specific segments with timestamps

For real-time voice and video interactions, see the
[Live API](/docs/live-api).
For dedicated speech to text models with support for real-time transcription,
use the [Google Cloud Speech-to-Text API](https://cloud.google.com/speech-to-text).

## Transcribe speech to text  {% id="speech-to-text" %}

This example shows how to transcribe, translate, and summarize speech with
timestamps, speaker diarization, and emotion detection using
[structured outputs](/docs/structured-output).

{% tabs %}
  {% tab label="Python" %}
  ```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-3.8-flash",
      input=[
          {"type": "video", "uri": YOUTUBE_URL, "mime_type": "video/mp4"},
          {"type": "text", "text": prompt}
      ],
      response_format=response_schema,
  )
  
  print(interaction.output_text)
  ```

  {% /tab %}

  {% tab label="JavaScript" %}
  ```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-3.8-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 || "{}"));
  ```

  {% /tab %}

  {% tab label="Java" %}
  ```java
  import com.google.genai.Client;
  import com.google.genai.gaos.models.interactions.Content;
  import com.google.genai.gaos.models.interactions.CreateModelInteraction;
  import com.google.genai.gaos.models.interactions.CreateModelInteractionResponseFormat;
  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.ResponseFormat;
  import com.google.genai.gaos.models.interactions.TextContent;
  import com.google.genai.gaos.models.interactions.VideoContent;
  import com.google.genai.gaos.models.interactions.VideoContentMimeType;
  import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
  import java.util.Arrays;
  import java.util.List;
  import java.util.HashMap;
  import java.util.Map;
  
  Client client = new Client();
  
  String youtubeUrl = "https://www.youtube.com/watch?v=ku-N-eS1lgM";
  
  String prompt =
      "Process the audio file and generate a detailed transcription.\n\n"
          + "Requirements:\n"
          + "1. Identify distinct speakers (e.g., Speaker 1, Speaker 2).\n"
          + "2. Provide accurate timestamps for each segment (Format: MM:SS).\n"
          + "3. Detect the primary language of each segment.\n"
          + "4. If not English, provide the English translation.\n"
          + "5. Identify the primary emotion: Happy, Sad, Angry, or Neutral.\n"
          + "6. Provide a brief summary at the beginning.";
  
  Map<String, Object> emotionProp = new HashMap<>();
  emotionProp.put("type", "string");
  emotionProp.put("enum", Arrays.asList("happy", "sad", "angry", "neutral"));
  
  Map<String, Object> stringType = new HashMap<>();
  stringType.put("type", "string");
  
  Map<String, Object> segmentProps = new HashMap<>();
  segmentProps.put("speaker", stringType);
  segmentProps.put("timestamp", stringType);
  segmentProps.put("content", stringType);
  segmentProps.put("language", stringType);
  segmentProps.put("emotion", emotionProp);
  
  Map<String, Object> segmentItem = new HashMap<>();
  segmentItem.put("type", "object");
  segmentItem.put("properties", segmentProps);
  segmentItem.put("required", Arrays.asList("speaker", "timestamp", "content", "emotion"));
  
  Map<String, Object> segmentsProp = new HashMap<>();
  segmentsProp.put("type", "array");
  segmentsProp.put("items", segmentItem);
  
  Map<String, Object> properties = new HashMap<>();
  properties.put("summary", stringType);
  properties.put("segments", segmentsProp);
  
  Map<String, Object> responseSchema = new HashMap<>();
  responseSchema.put("type", "object");
  responseSchema.put("properties", properties);
  responseSchema.put("required", Arrays.asList("summary", "segments"));
  
  Content videoContent =
      VideoContent.builder()
          .uri(youtubeUrl)
          .mimeType(VideoContentMimeType.VIDEO_MP4)
          .build();
  Content textContent = TextContent.builder().text(prompt).build();
  
  List<Content> contents = Arrays.asList(videoContent, textContent);
  
  CreateModelInteraction params =
      CreateModelInteraction.builder()
          .model(Model.of("gemini-3.8-flash"))
          .input(InteractionsInput.ofContent(contents))
          .responseFormat(
              CreateModelInteractionResponseFormat.of(ResponseFormat.of(responseSchema)))
          .build();
  
  Interaction interaction =
      client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
  
  System.out.println(interaction.outputText().orElse(""));
  ```

  {% /tab %}

  {% tab label="Go" %}
  ```go
  package main
  
  import (
      "context"
      "fmt"
      "log"
  
      "google.golang.org/genai"
      "google.golang.org/genai/interactions/models/interactions"
      "google.golang.org/genai/interactions/models/operations"
  )
  
  func main() {
      ctx := context.Background()
      client, err := genai.NewClient(ctx, nil)
      if err != nil {
          log.Fatal(err)
      }
  
      youtubeURL := "https://www.youtube.com/watch?v=ku-N-eS1lgM"
  
      prompt := "Process the audio file and generate a detailed transcription.\n\n" +
          "Requirements:\n" +
          "1. Identify distinct speakers (e.g., Speaker 1, Speaker 2).\n" +
          "2. Provide accurate timestamps for each segment (Format: MM:SS).\n" +
          "3. Detect the primary language of each segment.\n" +
          "4. If not English, provide the English translation.\n" +
          "5. Identify the primary emotion: Happy, Sad, Angry, or Neutral.\n" +
          "6. Provide a brief summary at the beginning."
  
      responseSchema := map[string]any{
          "type": "object",
          "properties": map[string]any{
              "summary": map[string]any{"type": "string"},
              "segments": map[string]any{
                  "type": "array",
                  "items": map[string]any{
                      "type": "object",
                      "properties": map[string]any{
                          "speaker":   map[string]any{"type": "string"},
                          "timestamp": map[string]any{"type": "string"},
                          "content":   map[string]any{"type": "string"},
                          "language":  map[string]any{"type": "string"},
                          "emotion": map[string]any{
                              "type": "string",
                              "enum": []string{"happy", "sad", "angry", "neutral"},
                          },
                      },
                      "required": []string{"speaker", "timestamp", "content", "emotion"},
                  },
              },
          },
          "required": []string{"summary", "segments"},
      }
  
      contents := []interactions.Content{
          interactions.NewContent(interactions.VideoContent{
              URI:      genai.Ptr(youtubeURL),
              MimeType: interactions.VideoContentMimeTypeVideoMp4.ToPointer(),
          }),
          interactions.NewContent(interactions.TextContent{
              Text: prompt,
          }),
      }
  
      res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
          Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
              Model: interactions.Model("gemini-3.8-flash"),
              Input: interactions.NewInteractionsInput(contents),
              ResponseFormat: genai.Ptr(interactions.NewCreateModelInteractionResponseFormat(
                  interactions.NewResponseFormat(responseSchema),
              )),
          }),
      })
      if err != nil {
          log.Fatal(err)
      }
  
      if res.Interaction.OutputText != nil {
          fmt.Println(*res.Interaction.OutputText)
      }
  }
  ```

  {% /tab %}

  {% tab label="REST" %}
  ```shell
  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-3.8-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"]}
                }
              }
            }
          }
        }
    }'
  ```

  {% /tab %}

{% /tabs %}

![](https://www.gstatic.com/cloud-cms/33400c9cca6dbde2006c54e54d5e19a5.gif)

## Input audio  {% id="input-audio" %}

You can provide audio data in the following ways:

* [Upload an audio file](/docs/audio#upload-audio) before making a request.
* [Pass inline audio data](/docs/audio#inline-audio) with the request.

### Upload an audio file  {% id="upload-audio" %}

Use the [Files API](/docs/files) for files larger than 20 MB.

{% tabs %}
  {% tab label="Python" %}
  ```python
  from google import genai
  
  client = genai.Client()
  
  uploaded_file = client.files.upload(file="path/to/sample.mp3")
  
  interaction = client.interactions.create(
      model="gemini-3.8-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)
  ```

  {% /tab %}

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

  {% /tab %}

  {% tab label="Java" %}
  ```java
  // Upload an audio file using the Files API (recommended for files > 20 MB)
  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 com.google.genai.types.File;
  import com.google.genai.types.UploadFileConfig;
  import java.util.Arrays;
  import java.util.List;
  
  Client client = new Client();
  
  File uploadedFile =
      client.files.upload(
          "path/to/sample.mp3", UploadFileConfig.builder().mimeType("audio/mp3").build());
  
  Content textContent = TextContent.builder().text("Describe this audio clip").build();
  Content audioContent =
      AudioContent.builder()
          .uri(uploadedFile.uri().get())
          .mimeType(AudioContentMimeType.of(uploadedFile.mimeType().get()))
          .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(""));
  ```

  {% /tab %}

  {% tab label="Go" %}
  ```go
  // Upload an audio file using the Files API (recommended for files > 20 MB)
  package main
  
  import (
      "context"
      "fmt"
      "log"
  
      "google.golang.org/genai"
      "google.golang.org/genai/interactions/models/interactions"
      "google.golang.org/genai/interactions/models/operations"
  )
  
  func main() {
      ctx := context.Background()
      client, err := genai.NewClient(ctx, nil)
      if err != nil {
          log.Fatal(err)
      }
  
      uploadedFile, err := client.Files.UploadFromPath(ctx, "path/to/sample.mp3", &genai.UploadFileConfig{
          MIMEType: "audio/mp3",
      })
      if err != nil {
          log.Fatal(err)
      }
  
      contents := []interactions.Content{
          interactions.NewContent(interactions.TextContent{
              Text: "Describe this audio clip",
          }),
          interactions.NewContent(interactions.AudioContent{
              URI:      genai.Ptr(uploadedFile.URI),
              MimeType: interactions.AudioContentMimeType(uploadedFile.MIMEType).ToPointer(),
          }),
      }
  
      res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
          Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
              Model: interactions.Model("gemini-3.8-flash"),
              Input: interactions.NewInteractionsInput(contents),
          }),
      })
      if err != nil {
          log.Fatal(err)
      }
  
      if res.Interaction.OutputText != nil {
          fmt.Println(*res.Interaction.OutputText)
      }
  }
  ```

  {% /tab %}

  {% tab label="REST" %}
  ```shell
  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-3.8-flash",
      "input": [
        {"type": "text", "text": "Describe this audio clip"},
        {
          "type": "audio",
          "uri": "YOUR_FILE_URI",
          "mime_type": "audio/mp3"
        }
      ]
    }'
  ```

  {% /tab %}

{% /tabs %}

### Pass audio data inline  {% id="inline-audio" %}

For small audio files under 20MB total request size:

{% tabs %}
  {% tab label="Python" %}
  ```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-3.8-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)
  ```

  {% /tab %}

  {% tab label="JavaScript" %}
  ```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-3.8-flash",
      input: [
          {type: "text", text: "Describe this audio clip"},
          {
              type: "audio",
              data: audioData,
              mime_type: "audio/mp3"
          }
      ]
  });
  console.log(interaction.output_text);
  ```

  {% /tab %}

  {% tab label="Java" %}
  ```java
  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.nio.file.Files;
  import java.nio.file.Paths;
  import java.util.Arrays;
  import java.util.Base64;
  import java.util.List;
  
  Client client = new Client();
  
  byte[] audioBytes = Files.readAllBytes(Paths.get("path/to/small-sample.mp3"));
  String base64Audio = Base64.getEncoder().encodeToString(audioBytes);
  
  Content textContent = TextContent.builder().text("Describe this audio clip").build();
  Content audioContent =
      AudioContent.builder()
          .data(base64Audio)
          .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(""));
  ```

  {% /tab %}

  {% tab label="Go" %}
  ```go
  package main
  
  import (
      "context"
      "encoding/base64"
      "fmt"
      "log"
      "os"
  
      "google.golang.org/genai"
      "google.golang.org/genai/interactions/models/interactions"
      "google.golang.org/genai/interactions/models/operations"
  )
  
  func main() {
      ctx := context.Background()
      client, err := genai.NewClient(ctx, nil)
      if err != nil {
          log.Fatal(err)
      }
  
      audioBytes, err := os.ReadFile("path/to/small-sample.mp3")
      if err != nil {
          log.Fatal(err)
      }
      base64Audio := base64.StdEncoding.EncodeToString(audioBytes)
  
      contents := []interactions.Content{
          interactions.NewContent(interactions.TextContent{
              Text: "Describe this audio clip",
          }),
          interactions.NewContent(interactions.AudioContent{
              Data:     genai.Ptr(base64Audio),
              MimeType: interactions.AudioContentMimeTypeAudioMp3.ToPointer(),
          }),
      }
  
      res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
          Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
              Model: interactions.Model("gemini-3.8-flash"),
              Input: interactions.NewInteractionsInput(contents),
          }),
      })
      if err != nil {
          log.Fatal(err)
      }
  
      if res.Interaction.OutputText != nil {
          fmt.Println(*res.Interaction.OutputText)
      }
  }
  ```

  {% /tab %}

  {% tab label="REST" %}
  ```shell
  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: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -H "Api-Revision: 2026-05-20" \
    -d '{
      "model": "gemini-3.8-flash",
      "input": [
        {"type": "text", "text": "Describe this audio clip"},
        {
          "type": "audio",
          "data": "'$(base64 $B64FLAGS $AUDIO_PATH)'",
          "mime_type": "audio/mp3"
        }
      ]
    }'
  ```

  {% /tab %}

{% /tabs %}

Notes on inline audio data:

* Maximum request size is 20 MB total (including prompts and all files)
* For reuse, [upload the file](/docs/audio#upload-audio) instead

## Get a transcript  {% id="transcript" %}

To get a transcript, ask for it in the prompt:

{% tabs %}
  {% tab label="Python" %}
  ```python
  interaction = client.interactions.create(
      model="gemini-3.8-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)
  ```

  {% /tab %}

  {% tab label="JavaScript" %}
  ```javascript
  const interaction = await client.interactions.create({
      model: "gemini-3.8-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);
  ```

  {% /tab %}

  {% tab label="Java" %}
  ```java
  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 com.google.genai.types.File;
  import com.google.genai.types.UploadFileConfig;
  import java.util.Arrays;
  import java.util.List;
  
  Client client = new Client();
  
  File uploadedFile =
      client.files.upload(
          "path/to/sample.mp3", UploadFileConfig.builder().mimeType("audio/mp3").build());
  
  Content textContent = TextContent.builder().text("Generate a transcript of the speech.").build();
  Content audioContent =
      AudioContent.builder()
          .uri(uploadedFile.uri().get())
          .mimeType(AudioContentMimeType.of(uploadedFile.mimeType().get()))
          .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(""));
  ```

  {% /tab %}

  {% tab label="Go" %}
  ```go
  package main
  
  import (
      "context"
      "fmt"
      "log"
  
      "google.golang.org/genai"
      "google.golang.org/genai/interactions/models/interactions"
      "google.golang.org/genai/interactions/models/operations"
  )
  
  func main() {
      ctx := context.Background()
      client, err := genai.NewClient(ctx, nil)
      if err != nil {
          log.Fatal(err)
      }
  
      uploadedFile, err := client.Files.UploadFromPath(ctx, "path/to/sample.mp3", &genai.UploadFileConfig{
          MIMEType: "audio/mp3",
      })
      if err != nil {
          log.Fatal(err)
      }
  
      contents := []interactions.Content{
          interactions.NewContent(interactions.TextContent{
              Text: "Generate a transcript of the speech.",
          }),
          interactions.NewContent(interactions.AudioContent{
              URI:      genai.Ptr(uploadedFile.URI),
              MimeType: interactions.AudioContentMimeType(uploadedFile.MIMEType).ToPointer(),
          }),
      }
  
      res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
          Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
              Model: interactions.Model("gemini-3.8-flash"),
              Input: interactions.NewInteractionsInput(contents),
          }),
      })
      if err != nil {
          log.Fatal(err)
      }
  
      if res.Interaction.OutputText != nil {
          fmt.Println(*res.Interaction.OutputText)
      }
  }
  ```

  {% /tab %}

{% /tabs %}

## Refer to timestamps  {% id="timestamps" %}

Use `MM:SS` format to reference specific sections:

{% tabs %}
  {% tab label="Python" %}
  ```python
  interaction = client.interactions.create(
      model="gemini-3.8-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
          }
      ]
  )
  ```

  {% /tab %}

  {% tab label="JavaScript" %}
  ```javascript
  const interaction = await client.interactions.create({
      model: "gemini-3.8-flash",
      input: [
          { type: "text", text: "Provide a transcript from 02:30 to 03:29." },
          { type: "audio", uri: uploadedFile.uri, mime_type: "audio/mp3" }
      ]
  });
  ```

  {% /tab %}

  {% tab label="Java" %}
  ```java
  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 com.google.genai.types.File;
  import com.google.genai.types.UploadFileConfig;
  import java.util.Arrays;
  import java.util.List;
  
  Client client = new Client();
  
  File uploadedFile =
      client.files.upload(
          "path/to/sample.mp3", UploadFileConfig.builder().mimeType("audio/mp3").build());
  
  Content textContent =
      TextContent.builder().text("Provide a transcript from 02:30 to 03:29.").build();
  Content audioContent =
      AudioContent.builder()
          .uri(uploadedFile.uri().get())
          .mimeType(AudioContentMimeType.of(uploadedFile.mimeType().get()))
          .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(""));
  ```

  {% /tab %}

  {% tab label="Go" %}
  ```go
  package main
  
  import (
      "context"
      "fmt"
      "log"
  
      "google.golang.org/genai"
      "google.golang.org/genai/interactions/models/interactions"
      "google.golang.org/genai/interactions/models/operations"
  )
  
  func main() {
      ctx := context.Background()
      client, err := genai.NewClient(ctx, nil)
      if err != nil {
          log.Fatal(err)
      }
  
      uploadedFile, err := client.Files.UploadFromPath(ctx, "path/to/sample.mp3", &genai.UploadFileConfig{
          MIMEType: "audio/mp3",
      })
      if err != nil {
          log.Fatal(err)
      }
  
      contents := []interactions.Content{
          interactions.NewContent(interactions.TextContent{
              Text: "Provide a transcript from 02:30 to 03:29.",
          }),
          interactions.NewContent(interactions.AudioContent{
              URI:      genai.Ptr(uploadedFile.URI),
              MimeType: interactions.AudioContentMimeType(uploadedFile.MIMEType).ToPointer(),
          }),
      }
  
      res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
          Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
              Model: interactions.Model("gemini-3.8-flash"),
              Input: interactions.NewInteractionsInput(contents),
          }),
      })
      if err != nil {
          log.Fatal(err)
      }
  
      if res.Interaction.OutputText != nil {
          fmt.Println(*res.Interaction.OutputText)
      }
  }
  ```

  {% /tab %}

{% /tabs %}

## Count tokens  {% id="count-tokens" %}

Count tokens in an audio file:

{% tabs %}
  {% tab label="Python" %}
  ```python
  response = client.models.count_tokens(
      model="gemini-3.8-flash",
      contents=[uploaded_file]
  )
  print(response)
  ```

  {% /tab %}

  {% tab label="JavaScript" %}
  ```javascript
  const response = await client.models.countTokens({
      model: "gemini-3.8-flash",
      contents: [
          { fileData: { fileUri: uploadedFile.uri, mimeType: uploadedFile.mimeType } }
      ]
  });
  console.log(response.totalTokens);
  ```

  {% /tab %}

  {% tab label="Java" %}
  ```java
  import com.google.genai.Client;
  import com.google.genai.types.Content;
  import com.google.genai.types.CountTokensResponse;
  import com.google.genai.types.File;
  import com.google.genai.types.Part;
  import com.google.genai.types.UploadFileConfig;
  import java.util.Arrays;
  
  Client client = new Client();
  
  File uploadedFile =
      client.files.upload(
          "path/to/sample.mp3", UploadFileConfig.builder().mimeType("audio/mp3").build());
  
  CountTokensResponse response =
      client.models.countTokens(
          "gemini-3.8-flash",
          Arrays.asList(
              Content.fromParts(
                  Part.fromUri(uploadedFile.uri().get(), uploadedFile.mimeType().get()))),
          null);
  
  System.out.println(response);
  ```

  {% /tab %}

  {% tab label="Go" %}
  ```go
  package main
  
  import (
      "context"
      "fmt"
      "log"
  
      "google.golang.org/genai"
  )
  
  func main() {
      ctx := context.Background()
      client, err := genai.NewClient(ctx, nil)
      if err != nil {
          log.Fatal(err)
      }
  
      uploadedFile, err := client.Files.UploadFromPath(ctx, "path/to/sample.mp3", &genai.UploadFileConfig{
          MIMEType: "audio/mp3",
      })
      if err != nil {
          log.Fatal(err)
      }
  
      response, err := client.Models.CountTokens(
          ctx,
          "gemini-3.8-flash",
          []*genai.Content{
              genai.NewContentFromURI(uploadedFile.URI, uploadedFile.MIMEType, genai.RoleUser),
          },
          nil,
      )
      if err != nil {
          log.Fatal(err)
      }
  
      fmt.Println(response.TotalTokens)
  }
  ```

  {% /tab %}

{% /tabs %}

## Supported audio formats  {% id="supported-formats" %}

Gemini supports the following audio format MIME types:

* WAV - `audio/wav`
* MP3 - `audio/mp3`
* AIFF - `audio/aiff`
* AAC - `audio/aac`
* OGG - `audio/ogg`
* FLAC - `audio/flac`
* MPEG - `audio/mpeg`
* M4A - `audio/m4a`
* L16 - `audio/l16`
* Opus - `audio/opus`
* ALAW - `audio/alaw`
* MULAW - `audio/mulaw`
* WebM - `audio/webm`

For the complete list of supported MIME types and parameter schemas, see the [Interactions API reference](https://ai.google.dev/api/interactions-api#Resource:Content).

## Technical details about audio  {% id="technical-details" %}

* **Tokens**: 32 tokens per second of audio (1 minute = 1,920 tokens)
* **Non-speech**: Gemini understands non-speech sounds (birdsong, sirens, etc.)
* **Max length**: 9.5 hours of audio per prompt
* **Resolution**: Downsampled to 16 Kbps
* **Channels**: Multi-channel audio combined to single channel

## What's next  {% id="whats-next" %}

*   [Files API](/docs/files): Upload and manage audio files

*   [System instructions](/docs/text-generation#system-instructions):
  Customize model behavior

*   [Structured output](/docs/structured-output):
  Get transcription results in JSON format