Audio understanding (speech only)

Python

To learn how to install or update the Vertex AI SDK for Python, see Install the Vertex AI SDK for Python. For more information, see the Vertex AI SDK for Python API reference documentation.

Streaming and non-streaming responses

You can choose whether the model generates streaming responses or non-streaming responses. For streaming responses, you receive each response as soon as its output token is generated. For non-streaming responses, you receive all responses after all of the output tokens are generated.

For a streaming response, use the stream parameter in generate_content.

  response = model.generate_content(contents=[...], stream = True)
  

For a non-streaming response, remove the parameter, or set the parameter to False.

Sample code

import vertexai
from vertexai.generative_models import GenerativeModel, Part

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")

prompt = """
Please provide a summary for the audio.
Provide chapter titles, be concise and short, no need to provide chapter summaries.
Do not make up any information that is not part of the audio and do not be verbose.
"""

audio_file_uri = "gs://cloud-samples-data/generative-ai/audio/pixel.mp3"
audio_file = Part.from_uri(audio_file_uri, mime_type="audio/mpeg")

contents = [audio_file, prompt]

response = model.generate_content(contents)
print(response.text)
# Example response:
# **Made By Google Podcast Summary**
# **Chapter Titles:**
# * Introduction
# * Transformative Pixel Features
# ...

Java

Before trying this sample, follow the Java setup instructions in the Vertex AI quickstart. For more information, see the Vertex AI Java SDK for Gemini reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

Streaming and non-streaming responses

You can choose whether the model generates streaming responses or non-streaming responses. For streaming responses, you receive each response as soon as its output token is generated. For non-streaming responses, you receive all responses after all of the output tokens are generated.

For a streaming response, use the generateContentStream method.

  public ResponseStream<GenerateContentResponse> generateContentStream(Content content)
  

For a non-streaming response, use the generateContent method.

  public GenerateContentResponse generateContent(Content content)
  

Sample code

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.ContentMaker;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.PartMaker;
import com.google.cloud.vertexai.generativeai.ResponseHandler;
import java.io.IOException;

public class AudioInputSummarization {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    summarizeAudio(projectId, location, modelName);
  }

  // Analyzes the given audio input.
  public static String summarizeAudio(String projectId, String location, String modelName)
      throws IOException {
    // Initialize client that will be used to send requests. This client only needs
    // to be created once, and can be reused for multiple requests.
    try (VertexAI vertexAI = new VertexAI(projectId, location)) {
      String audioUri = "gs://cloud-samples-data/generative-ai/audio/pixel.mp3";

      GenerativeModel model = new GenerativeModel(modelName, vertexAI);
      GenerateContentResponse response = model.generateContent(
          ContentMaker.fromMultiModalData(
              "Please provide a summary for the audio.\n"
                  + "Provide chapter titles with timestamps, be concise and short, "
                  + "no need to provide chapter summaries.\n"
                  + "Do not make up any information that is not part of the audio "
                  + "and do not be verbose.",
              PartMaker.fromMimeTypeAndData("audio/mp3", audioUri)
          ));

      String output = ResponseHandler.getText(response);
      System.out.println(output);

      return output;
    }
  }
}

Node.js

Before trying this sample, follow the Node.js setup instructions in the Generative AI quickstart using the Node.js SDK. For more information, see the Node.js SDK for Gemini reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

Streaming and non-streaming responses

You can choose whether the model generates streaming responses or non-streaming responses. For streaming responses, you receive each response as soon as its output token is generated. For non-streaming responses, you receive all responses after all of the output tokens are generated.

For a streaming response, use the generateContentStream method.

  const streamingResp = await generativeModel.generateContentStream(request);
  

For a non-streaming response, use the generateContent method.

  const streamingResp = await generativeModel.generateContent(request);
  

Sample code

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function summarize_audio(projectId = 'PROJECT_ID') {
  const vertexAI = new VertexAI({project: projectId, location: 'us-central1'});

  const generativeModel = vertexAI.getGenerativeModel({
    model: 'gemini-1.5-flash-001',
  });

  const filePart = {
    file_data: {
      file_uri: 'gs://cloud-samples-data/generative-ai/audio/pixel.mp3',
      mime_type: 'audio/mpeg',
    },
  };
  const textPart = {
    text: `
    Please provide a summary for the audio.
    Provide chapter titles with timestamps, be concise and short, no need to provide chapter summaries.
    Do not make up any information that is not part of the audio and do not be verbose.`,
  };

  const request = {
    contents: [{role: 'user', parts: [filePart, textPart]}],
  };

  const resp = await generativeModel.generateContent(request);
  const contentResponse = await resp.response;
  console.log(JSON.stringify(contentResponse));
}

Go

Before trying this sample, follow the Go setup instructions in the Vertex AI quickstart. For more information, see the Vertex AI Go SDK for Gemini reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

Streaming and non-streaming responses

You can choose whether the model generates streaming responses or non-streaming responses. For streaming responses, you receive each response as soon as its output token is generated. For non-streaming responses, you receive all responses after all of the output tokens are generated.

For a streaming response, use the GenerateContentStream method.

  iter := model.GenerateContentStream(ctx, genai.Text("Tell me a story about a lumberjack and his giant ox. Keep it very short."))
  

For a non-streaming response, use the GenerateContent method.

  resp, err := model.GenerateContent(ctx, genai.Text("What is the average size of a swallow?"))
  

Sample code

import (
	"context"
	"errors"
	"fmt"
	"io"
	"mime"
	"path/filepath"

	"cloud.google.com/go/vertexai/genai"
)

// summarizeAudio shows how to send an audio asset and a text question to a model, writing the response to the
// provided io.Writer.
func summarizeAudio(w io.Writer, projectID, location, modelName string) error {
	// location := "us-central1"
	// modelName := "gemini-1.5-flash-001"
	ctx := context.Background()

	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)
	model.SetTemperature(0.4)

	// Given an audio file URL, prepare audio file as genai.Part
	part := genai.FileData{
		MIMEType: mime.TypeByExtension(filepath.Ext("pixel.mp3")),
		FileURI:  "gs://cloud-samples-data/generative-ai/audio/pixel.mp3",
	}

	res, err := model.GenerateContent(ctx, part, genai.Text(`
		Please provide a summary for the audio.
		Provide chapter titles with timestamps, be concise and short, no need to provide chapter summaries.
		Do not make up any information that is not part of the audio and do not be verbose.
	`,
	))
	if err != nil {
		return fmt.Errorf("unable to generate contents: %w", err)
	}

	if len(res.Candidates) == 0 ||
		len(res.Candidates[0].Content.Parts) == 0 {
		return errors.New("empty response from model")
	}

	fmt.Fprintf(w, "generated summary:\n%s\n", res.Candidates[0].Content.Parts[0])
	return nil
}

C#

Before trying this sample, follow the C# setup instructions in the Vertex AI quickstart. For more information, see the Vertex AI C# reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

Streaming and non-streaming responses

You can choose whether the model generates streaming responses or non-streaming responses. For streaming responses, you receive each response as soon as its output token is generated. For non-streaming responses, you receive all responses after all of the output tokens are generated.

For a streaming response, use the StreamGenerateContent method.

  public virtual PredictionServiceClient.StreamGenerateContentStream StreamGenerateContent(GenerateContentRequest request)
  

For a non-streaming response, use the GenerateContentAsync method.

  public virtual Task<GenerateContentResponse> GenerateContentAsync(GenerateContentRequest request)
  

For more information on how the server can stream responses, see Streaming RPCs.

Sample code

using Google.Cloud.AIPlatform.V1;
using System;
using System.Threading.Tasks;

public class AudioInputSummarization
{
    public async Task<string> SummarizeAudio(
        string projectId = "your-project-id",
        string location = "us-central1",
        string publisher = "google",
        string model = "gemini-1.5-flash-001")
    {
        var predictionServiceClient = new PredictionServiceClientBuilder
        {
            Endpoint = $"{location}-aiplatform.googleapis.com"
        }.Build();

        string prompt = @"Please provide a summary for the audio.
Provide chapter titles with timestamps, be concise and short, no need to provide chapter summaries.
Do not make up any information that is not part of the audio and do not be verbose.";

        var generateContentRequest = new GenerateContentRequest
        {
            Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
            Contents =
            {
                new Content
                {
                    Role = "USER",
                    Parts =
                    {
                        new Part { Text = prompt },
                        new Part { FileData = new() { MimeType = "audio/mp3", FileUri = "gs://cloud-samples-data/generative-ai/audio/pixel.mp3" } }
                    }
                }
            }
        };

        GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(generateContentRequest);

        string responseText = response.Candidates[0].Content.Parts[0].Text;
        Console.WriteLine(responseText);

        return responseText;
    }
}

REST

After you set up your environment, you can use REST to test a text prompt. The following sample sends a request to the publisher model endpoint.

Before using any of the request data, make the following replacements:

• LOCATION: The region to process the request. Enter a supported region. For the full list of supported regions, see Available locations.

  Click to expand a partial list of available regions

  • us-central1
  • us-west4
  • northamerica-northeast1
  • us-east4
  • us-west1
  • asia-northeast3
  • asia-southeast1
  • asia-northeast1
• PROJECT_ID: Your project ID.
• FILE_URI: The URI or URL of the file to include in the prompt. Acceptable values include the following:
  • Cloud Storage bucket URI: The object must either be publicly readable or reside in the same Google Cloud project that's sending the request. For gemini-1.5-pro and gemini-1.5-flash, the size limit is 2 GB. For gemini-1.0-pro-vision, the size limit is 20 MB.
  • HTTP URL: The file URL must be publicly readable. You can specify one video file and up to 10 image files per request. Audio files and documents can't exceed 15 MB.
  • YouTube video URL:The YouTube video must be either owned by the account that you used to sign in to the Google Cloud console or is public. Only one YouTube video URL is supported per request.

  When specifying a fileURI, you must also specify the media type (mimeType) of the file.

  If you don't have an audio file in Cloud Storage, then you can use the following publicly available file: gs://cloud-samples-data/generative-ai/audio/pixel.mp3 with a mime type of audio/mp3. To listen to this audio, open the sample MP3 file.

• MIME_TYPE: The media type of the file specified in the data or fileUri fields. Acceptable values include the following:

  Click to expand MIME types

  • application/pdf
  • audio/mpeg
  • audio/mp3
  • audio/wav
  • image/png
  • image/jpeg
  • image/webp
  • text/plain
  • video/mov
  • video/mpeg
  • video/mp4
  • video/mpg
  • video/avi
  • video/wmv
  • video/mpegps
  • video/flv
• TEXT

  The text instructions to include in the prompt. For example, Please provide a summary for the audio. Provide chapter titles, be concise and short, no need to provide chapter summaries. Do not make up any information that is not part of the audio and do not be verbose.

To send your request, choose one of these options:

cat > request.json << 'EOF'
{
  "contents": {
    "role": "USER",
    "parts": [
      {
        "fileData": {
          "fileUri": "FILE_URI",
          "mimeType": "MIME_TYPE"
        }
      },
      {
        "text": "TEXT"
      }
    ]
  }
}
EOF

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/gemini-1.5-flash:generateContent"

@'
{
  "contents": {
    "role": "USER",
    "parts": [
      {
        "fileData": {
          "fileUri": "FILE_URI",
          "mimeType": "MIME_TYPE"
        }
      },
      {
        "text": "TEXT"
      }
    ]
  }
}
'@  | Out-File -FilePath request.json -Encoding utf8

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/gemini-1.5-flash:generateContent" | Select-Object -Expand Content

You should receive a JSON response similar to the following.

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "## Made By Google Podcast - Pixel Feature Drops \n\n**Chapter 1: Transformative Pixel Features**\n\n**Chapter 2: Importance of Feature Drops**\n\n**Chapter 3: January's Feature Drop Highlights**\n\n**Chapter 4: March's Feature Drop Highlights for Pixel Watch**\n\n**Chapter 5: March's Feature Drop Highlights for Pixel Phones**\n\n**Chapter 6: Feature Drop Expansion to Other Devices**\n\n**Chapter 7: Deciding Which Features to Include in Feature Drops**\n\n**Chapter 8: Importance of User Feedback**\n\n**Chapter 9: When to Expect March's Feature Drop**\n\n**Chapter 10: Stand-Out Features from Past Feature Drops** \n"
          }
        ]
      },
      "finishReason": "STOP",
      "safetyRatings": [
        {
          "category": "HARM_CATEGORY_HATE_SPEECH",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.05470151,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.07864238
        },
        {
          "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.027742893,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.050051305
        },
        {
          "category": "HARM_CATEGORY_HARASSMENT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.08678674,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.06108711
        },
        {
          "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.11899801,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.14706452
        }
      ]
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 18883,
    "candidatesTokenCount": 150,
    "totalTokenCount": 19033
  }
}

• Use the generateContent method to request that the response is returned after it's fully generated. To reduce the perception of latency to a human audience, stream the response as it's being generated by using the streamGenerateContent method.
• The multimodal model ID is located at the end of the URL before the method (for example, gemini-1.5-flash or gemini-1.0-pro-vision). This sample may support other models as well.

Console

1. In the Vertex AI section of the Google Cloud console, go to the Vertex AI Studio page.

   Go to Vertex AI Studio

2. Click Open freeform.

3. Optional: Configure the model and parameters:

   • Model: Select a model.
   • Region: Select the region that you want to use.

   • Temperature: Use the slider or textbox to enter a value for temperature.

     The temperature is used for sampling during response generation, which occurs when topP and topK are applied. Temperature controls the degree of randomness in token selection. Lower temperatures are good for prompts that require a less open-ended or creative response, while higher temperatures can lead to more diverse or creative results. A temperature of 0 means that the highest probability tokens are always selected. In this case, responses for a given prompt are mostly deterministic, but a small amount of variation is still possible.

     If the model returns a response that's too generic, too short, or the model gives a fallback response, try increasing the temperature.

   • Output token limit: Use the slider or textbox to enter a value for the max output limit.

     Maximum number of tokens that can be generated in the response. A token is approximately four characters. 100 tokens correspond to roughly 60-80 words.

     Specify a lower value for shorter responses and a higher value for potentially longer responses.

   • Add stop sequence: Optional. Enter a stop sequence, which is a series of characters that includes spaces. If the model encounters a stop sequence, the response generation stops. The stop sequence isn't included in the response, and you can add up to five stop sequences.

4. Optional: To configure advanced parameters, click Advanced and configure as follows:

   Click to expand advanced configurations

   • Top-K: Use the slider or textbox to enter a value for top-K. (not supported for Gemini 1.5).

     Top-K changes how the model selects tokens for output. A top-K of 1 means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a top-K of 3 means that the next token is selected from among the three most probable tokens by using temperature.

     For each token selection step, the top-K tokens with the highest probabilities are sampled. Then tokens are further filtered based on top-P with the final token selected using temperature sampling.

     Specify a lower value for less random responses and a higher value for more random responses.

   • Top-P: Use the slider or textbox to enter a value for top-P. Tokens are selected from most probable to the least until the sum of their probabilities equals the value of top-P. For the least variable results, set top-P to 0.
   • Max responses: Use the slider or textbox to enter a value for the number of responses to generate.
   • Streaming responses: Enable to print responses as they're generated.
   • Safety filter threshold: Select the threshold of how likely you are to see responses that could be harmful.
   • Enable Grounding: Grounding isn't supported for multimodal prompts.

5. Click Insert Media, and select a source for your file.

   Upload

   Select the file that you want to upload and click Open.

   By URL

   Enter the URL of the file that you want to use and click Insert.

   Cloud Storage

   Select the bucket and then the file from the bucket that you want to import and click Select.

   Google Drive

   1. Choose an account and give consent to Vertex AI Studio to access your account the first time you select this option. You can upload multiple files that have a total size of up to 10 MB. A single file can't exceed 7 MB.
   2. Click the file that you want to add.

   3. Click Select.

      The file thumbnail displays in the Prompt pane. The total number of tokens also displays. If your prompt data exceeds the token limit, the tokens are truncated and aren't included in processing your data.

6. Enter your text prompt in the Prompt pane.

7. Optional: To view the Token ID to text and Token IDs, click the tokens count in the Prompt pane.

8. Click Submit.

9. Optional: To save your prompt to My prompts, click save_alt Save.

10. Optional: To get the Python code or a curl command for your prompt, click code Get code.

Python

To learn how to install or update the Vertex AI SDK for Python, see Install the Vertex AI SDK for Python. For more information, see the Vertex AI SDK for Python API reference documentation.

Streaming and non-streaming responses

You can choose whether the model generates streaming responses or non-streaming responses. For streaming responses, you receive each response as soon as its output token is generated. For non-streaming responses, you receive all responses after all of the output tokens are generated.

For a streaming response, use the stream parameter in generate_content.

  response = model.generate_content(contents=[...], stream = True)
  

For a non-streaming response, remove the parameter, or set the parameter to False.

Sample code

import vertexai
from vertexai.generative_models import GenerativeModel, GenerationConfig, Part

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")

prompt = """
Can you transcribe this interview, in the format of timecode, speaker, caption.
Use speaker A, speaker B, etc. to identify speakers.
"""

audio_file_uri = "gs://cloud-samples-data/generative-ai/audio/pixel.mp3"
audio_file = Part.from_uri(audio_file_uri, mime_type="audio/mpeg")

contents = [audio_file, prompt]

response = model.generate_content(contents, generation_config=GenerationConfig(audio_timestamp=True))

print(response.text)
# Example response:
# [00:00:00] Speaker A: Your devices are getting better over time...
# [00:00:16] Speaker B: Welcome to the Made by Google podcast, ...
# [00:01:00] Speaker A: So many features. I am a singer. ...
# [00:01:33] Speaker B: Amazing. DeCarlos, same question to you, ...

Java

Before trying this sample, follow the Java setup instructions in the Vertex AI quickstart. For more information, see the Vertex AI Java SDK for Gemini reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

Streaming and non-streaming responses

You can choose whether the model generates streaming responses or non-streaming responses. For streaming responses, you receive each response as soon as its output token is generated. For non-streaming responses, you receive all responses after all of the output tokens are generated.

For a streaming response, use the generateContentStream method.

  public ResponseStream<GenerateContentResponse> generateContentStream(Content content)
  

For a non-streaming response, use the generateContent method.

  public GenerateContentResponse generateContent(Content content)
  

Sample code

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.ContentMaker;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.PartMaker;
import com.google.cloud.vertexai.generativeai.ResponseHandler;
import java.io.IOException;

public class AudioInputTranscription {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    transcribeAudio(projectId, location, modelName);
  }

  // Analyzes the given audio input.
  public static String transcribeAudio(String projectId, String location, String modelName)
      throws IOException {
    // Initialize client that will be used to send requests. This client only needs
    // to be created once, and can be reused for multiple requests.
    try (VertexAI vertexAI = new VertexAI(projectId, location)) {
      String audioUri = "gs://cloud-samples-data/generative-ai/audio/pixel.mp3";

      GenerativeModel model = new GenerativeModel(modelName, vertexAI);
      GenerateContentResponse response = model.generateContent(
          ContentMaker.fromMultiModalData(
              "Can you transcribe this interview, in the format of timecode, speaker, caption.\n"
                  + "Use speaker A, speaker B, etc. to identify speakers.",
              PartMaker.fromMimeTypeAndData("audio/mp3", audioUri)
          ));

      String output = ResponseHandler.getText(response);
      System.out.println(output);

      return output;
    }
  }
}

Node.js

Before trying this sample, follow the Node.js setup instructions in the Generative AI quickstart using the Node.js SDK. For more information, see the Node.js SDK for Gemini reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

Streaming and non-streaming responses

You can choose whether the model generates streaming responses or non-streaming responses. For streaming responses, you receive each response as soon as its output token is generated. For non-streaming responses, you receive all responses after all of the output tokens are generated.

For a streaming response, use the generateContentStream method.

  const streamingResp = await generativeModel.generateContentStream(request);
  

For a non-streaming response, use the generateContent method.

  const streamingResp = await generativeModel.generateContent(request);
  

Sample code

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function transcript_audio(projectId = 'PROJECT_ID') {
  const vertexAI = new VertexAI({project: projectId, location: 'us-central1'});

  const generativeModel = vertexAI.getGenerativeModel({
    model: 'gemini-1.5-flash-001',
  });

  const filePart = {
    file_data: {
      file_uri: 'gs://cloud-samples-data/generative-ai/audio/pixel.mp3',
      mime_type: 'audio/mpeg',
    },
  };
  const textPart = {
    text: `
    Can you transcribe this interview, in the format of timecode, speaker, caption?
    Use speaker A, speaker B, etc. to identify speakers.`,
  };

  const request = {
    contents: [{role: 'user', parts: [filePart, textPart]}],
  };

  const resp = await generativeModel.generateContent(request);
  const contentResponse = await resp.response;
  console.log(JSON.stringify(contentResponse));
}

Go

Before trying this sample, follow the Go setup instructions in the Vertex AI quickstart. For more information, see the Vertex AI Go SDK for Gemini reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

Streaming and non-streaming responses

You can choose whether the model generates streaming responses or non-streaming responses. For streaming responses, you receive each response as soon as its output token is generated. For non-streaming responses, you receive all responses after all of the output tokens are generated.

For a streaming response, use the GenerateContentStream method.

  iter := model.GenerateContentStream(ctx, genai.Text("Tell me a story about a lumberjack and his giant ox. Keep it very short."))
  

For a non-streaming response, use the GenerateContent method.

  resp, err := model.GenerateContent(ctx, genai.Text("What is the average size of a swallow?"))
  

Sample code

import (
	"context"
	"errors"
	"fmt"
	"io"
	"mime"
	"path/filepath"

	"cloud.google.com/go/vertexai/genai"
)

// transcribeAudio generates a response into w
func transcribeAudio(w io.Writer, projectID, location, modelName string) error {
	// location := "us-central1"
	// modelName := "gemini-1.5-flash-001"

	ctx := context.Background()

	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)

	// Optional: set an explicit temperature
	model.SetTemperature(0.4)

	// Given an audio file URL, prepare audio file as genai.Part
	img := genai.FileData{
		MIMEType: mime.TypeByExtension(filepath.Ext("pixel.mp3")),
		FileURI:  "gs://cloud-samples-data/generative-ai/audio/pixel.mp3",
	}

	res, err := model.GenerateContent(ctx, img, genai.Text(`
			Can you transcribe this interview, in the format of timecode, speaker, caption.
			Use speaker A, speaker B, etc. to identify speakers.
	`))
	if err != nil {
		return fmt.Errorf("unable to generate contents: %w", err)
	}

	if len(res.Candidates) == 0 ||
		len(res.Candidates[0].Content.Parts) == 0 {
		return errors.New("empty response from model")
	}

	fmt.Fprintf(w, "generated transcript:\n%s\n", res.Candidates[0].Content.Parts[0])
	return nil
}

C#

Before trying this sample, follow the C# setup instructions in the Vertex AI quickstart. For more information, see the Vertex AI C# reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

Streaming and non-streaming responses

You can choose whether the model generates streaming responses or non-streaming responses. For streaming responses, you receive each response as soon as its output token is generated. For non-streaming responses, you receive all responses after all of the output tokens are generated.

For a streaming response, use the StreamGenerateContent method.

  public virtual PredictionServiceClient.StreamGenerateContentStream StreamGenerateContent(GenerateContentRequest request)
  

For a non-streaming response, use the GenerateContentAsync method.

  public virtual Task<GenerateContentResponse> GenerateContentAsync(GenerateContentRequest request)
  

For more information on how the server can stream responses, see Streaming RPCs.

Sample code

using Google.Cloud.AIPlatform.V1;
using System;
using System.Threading.Tasks;

public class AudioInputTranscription
{
    public async Task<string> TranscribeAudio(
        string projectId = "your-project-id",
        string location = "us-central1",
        string publisher = "google",
        string model = "gemini-1.5-flash-001")
    {

        var predictionServiceClient = new PredictionServiceClientBuilder
        {
            Endpoint = $"{location}-aiplatform.googleapis.com"
        }.Build();

        string prompt = @"Can you transcribe this interview, in the format of timecode, speaker, caption.
Use speaker A, speaker B, etc. to identify speakers.";

        var generateContentRequest = new GenerateContentRequest
        {
            Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
            Contents =
            {
                new Content
                {
                    Role = "USER",
                    Parts =
                    {
                        new Part { Text = prompt },
                        new Part { FileData = new() { MimeType = "audio/mp3", FileUri = "gs://cloud-samples-data/generative-ai/audio/pixel.mp3" } }
                    }
                }
            }
        };

        GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(generateContentRequest);

        string responseText = response.Candidates[0].Content.Parts[0].Text;
        Console.WriteLine(responseText);

        return responseText;
    }
}

REST

After you set up your environment, you can use REST to test a text prompt. The following sample sends a request to the publisher model endpoint.

Before using any of the request data, make the following replacements:

• LOCATION: The region to process the request. Enter a supported region. For the full list of supported regions, see Available locations.

  Click to expand a partial list of available regions

  • us-central1
  • us-west4
  • northamerica-northeast1
  • us-east4
  • us-west1
  • asia-northeast3
  • asia-southeast1
  • asia-northeast1
• PROJECT_ID: Your project ID.
• FILE_URI: The URI or URL of the file to include in the prompt. Acceptable values include the following:
  • Cloud Storage bucket URI: The object must either be publicly readable or reside in the same Google Cloud project that's sending the request. For gemini-1.5-pro and gemini-1.5-flash, the size limit is 2 GB. For gemini-1.0-pro-vision, the size limit is 20 MB.
  • HTTP URL: The file URL must be publicly readable. You can specify one video file and up to 10 image files per request. Audio files and documents can't exceed 15 MB.
  • YouTube video URL:The YouTube video must be either owned by the account that you used to sign in to the Google Cloud console or is public. Only one YouTube video URL is supported per request.

  When specifying a fileURI, you must also specify the media type (mimeType) of the file.

  If you don't have an audio file in Cloud Storage, then you can use the following publicly available file: gs://cloud-samples-data/generative-ai/audio/pixel.mp3 with a mime type of audio/mp3. To listen to this audio, open the sample MP3 file.

• MIME_TYPE: The media type of the file specified in the data or fileUri fields. Acceptable values include the following:

  Click to expand MIME types

  • application/pdf
  • audio/mpeg
  • audio/mp3
  • audio/wav
  • image/png
  • image/jpeg
  • image/webp
  • text/plain
  • video/mov
  • video/mpeg
  • video/mp4
  • video/mpg
  • video/avi
  • video/wmv
  • video/mpegps
  • video/flv
• TEXT

  The text instructions to include in the prompt. For example, Can you transcribe this interview, in the format of timecode, speaker, caption. Use speaker A, speaker B, etc. to identify speakers.

To send your request, choose one of these options:

cat > request.json << 'EOF'
{
  "contents": {
    "role": "USER",
    "parts": [
      {
        "fileData": {
          "fileUri": "FILE_URI",
          "mimeType": "MIME_TYPE"
        }
      },
      {
        "text": "TEXT"
      }
    ]
  },
  "generatationConfig": {
    "audioTimestamp": true
  }
}
EOF

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/gemini-1.5-flash:generateContent"

@'
{
  "contents": {
    "role": "USER",
    "parts": [
      {
        "fileData": {
          "fileUri": "FILE_URI",
          "mimeType": "MIME_TYPE"
        }
      },
      {
        "text": "TEXT"
      }
    ]
  },
  "generatationConfig": {
    "audioTimestamp": true
  }
}
'@  | Out-File -FilePath request.json -Encoding utf8

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/gemini-1.5-flash:generateContent" | Select-Object -Expand Content

You should receive a JSON response similar to the following.

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "0:00 Speaker A: Your devices are getting better over time, and so we think
              about it across the entire portfolio from phones to watch to buds to tablet. We get
              really excited about how we can tell a joint narrative across everything.
              0:18 Speaker B: Welcome to the Made By Google Podcast, where we meet the people who
              work on the Google products you love. Here's your host, Rasheed.
              0:33 Speaker B: Today we're talking to Aisha and DeCarlos. They're both
              Product Managers for various Pixel devices and work on something that all the Pixel
              owners love. The Pixel feature drops. This is the Made By Google Podcast. Aisha, which
              feature on your Pixel phone has been most transformative in your own life?
              0:56 Speaker A: So many features. I am a singer, so I actually think recorder
              transcription has been incredible because before I would record songs I'd just like,
              freestyle them, record them, type them up. But now with transcription it works so well
              even deciphering lyrics that are jumbled. I think that's huge.
              ...
              Subscribe now wherever you get your podcasts to be the first to listen."
          }
        ]
      },
      "finishReason": "STOP",
      "safetyRatings": [
        {
          "category": "HARM_CATEGORY_HATE_SPEECH",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.043609526,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.06255973
        },
        {
          "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.022328783,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.04426588
        },
        {
          "category": "HARM_CATEGORY_HARASSMENT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.07107367,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.049405243
        },
        {
          "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
          "probability": "NEGLIGIBLE",
          "probabilityScore": 0.10484337,
          "severity": "HARM_SEVERITY_NEGLIGIBLE",
          "severityScore": 0.13128456
        }
      ]
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 18871,
    "candidatesTokenCount": 2921,
    "totalTokenCount": 21792
  }
}

• Use the generateContent method to request that the response is returned after it's fully generated. To reduce the perception of latency to a human audience, stream the response as it's being generated by using the streamGenerateContent method.
• The multimodal model ID is located at the end of the URL before the method (for example, gemini-1.5-flash or gemini-1.0-pro-vision). This sample may support other models as well.

Console

1. In the Vertex AI section of the Google Cloud console, go to the Vertex AI Studio page.

   Go to Vertex AI Studio

2. Click Open freeform.

3. Optional: Configure the model and parameters:

   • Model: Select a model.
   • Region: Select the region that you want to use.

   • Temperature: Use the slider or textbox to enter a value for temperature.

     The temperature is used for sampling during response generation, which occurs when topP and topK are applied. Temperature controls the degree of randomness in token selection. Lower temperatures are good for prompts that require a less open-ended or creative response, while higher temperatures can lead to more diverse or creative results. A temperature of 0 means that the highest probability tokens are always selected. In this case, responses for a given prompt are mostly deterministic, but a small amount of variation is still possible.

     If the model returns a response that's too generic, too short, or the model gives a fallback response, try increasing the temperature.

   • Output token limit: Use the slider or textbox to enter a value for the max output limit.

     Maximum number of tokens that can be generated in the response. A token is approximately four characters. 100 tokens correspond to roughly 60-80 words.

     Specify a lower value for shorter responses and a higher value for potentially longer responses.

   • Add stop sequence: Optional. Enter a stop sequence, which is a series of characters that includes spaces. If the model encounters a stop sequence, the response generation stops. The stop sequence isn't included in the response, and you can add up to five stop sequences.

4. Optional: To configure advanced parameters, click Advanced and configure as follows:

   Click to expand advanced configurations

   • Top-K: Use the slider or textbox to enter a value for top-K. (not supported for Gemini 1.5).

     Top-K changes how the model selects tokens for output. A top-K of 1 means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a top-K of 3 means that the next token is selected from among the three most probable tokens by using temperature.

     For each token selection step, the top-K tokens with the highest probabilities are sampled. Then tokens are further filtered based on top-P with the final token selected using temperature sampling.

     Specify a lower value for less random responses and a higher value for more random responses.

   • Top-P: Use the slider or textbox to enter a value for top-P. Tokens are selected from most probable to the least until the sum of their probabilities equals the value of top-P. For the least variable results, set top-P to 0.
   • Max responses: Use the slider or textbox to enter a value for the number of responses to generate.
   • Streaming responses: Enable to print responses as they're generated.
   • Safety filter threshold: Select the threshold of how likely you are to see responses that could be harmful.
   • Enable Grounding: Grounding isn't supported for multimodal prompts.

5. Click Insert Media, and select a source for your file.

   Upload

   Select the file that you want to upload and click Open.

   By URL

   Enter the URL of the file that you want to use and click Insert.

   Cloud Storage

   Select the bucket and then the file from the bucket that you want to import and click Select.

   Google Drive

   1. Choose an account and give consent to Vertex AI Studio to access your account the first time you select this option. You can upload multiple files that have a total size of up to 10 MB. A single file can't exceed 7 MB.
   2. Click the file that you want to add.

   3. Click Select.

      The file thumbnail displays in the Prompt pane. The total number of tokens also displays. If your prompt data exceeds the token limit, the tokens are truncated and aren't included in processing your data.

6. Enter your text prompt in the Prompt pane.

7. Optional: To view the Token ID to text and Token IDs, click the tokens count in the Prompt pane.

8. Click Submit.

9. Optional: To save your prompt to My prompts, click save_alt Save.

10. Optional: To get the Python code or a curl command for your prompt, click code Get code.