টেক্সট-টু-স্পিচ জেনারেশন (TTS)

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash-tts",
    input=[{
        "type": "user_input",
        "content": [{
            "type": "text",
            "text": "Have a wonderful day!",
            "annotations": [{
                "type": "speech_metadata",
                "style": "cheerful and friendly",
            }],
        }],
    }],
    response_format={"type": "audio"},
    generation_config={
        "speech_config": [
            {"voice": "Kore"},
        ]
    },
)

with open("out.wav", "wb") as f:
    f.write(base64.b64decode(interaction.output_audio.data))

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

async function main() {
   const client = new GoogleGenAI({});

   const interaction = await client.interactions.create({
      model: 'gemini-3.8-flash-tts',
      input: [{
         type: 'user_input',
         content: [{
            type: 'text',
            text: 'Have a wonderful day!',
            annotations: [{
               type: 'speech_metadata',
               style: 'cheerful and friendly',
            }],
         }],
      }],
      response_format: { type: 'audio' },
      generation_config: {
         speech_config: [
            { voice: 'Kore' },
         ],
      },
   });

   const audioBuffer = Buffer.from(interaction.output_audio.data, 'base64');
   fs.writeFileSync('out.wav', audioBuffer);
}
await main();

package main

import (
    "context"
    "encoding/base64"
    "encoding/binary"
    "log"
    "os"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func saveWaveFile(filename string, pcmData []byte) error {
    f, err := os.Create(filename)
    if err != nil {
        return err
    }
    defer f.Close()

    sampleRate := uint32(24000)
    numChannels := uint16(1)
    bitsPerSample := uint16(16)
    byteRate := sampleRate * uint32(numChannels) * uint32(bitsPerSample/8)
    blockAlign := numChannels * (bitsPerSample / 8)
    dataSize := uint32(len(pcmData))

    f.WriteString("RIFF")
    binary.Write(f, binary.LittleEndian, uint32(36+dataSize))
    f.WriteString("WAVEfmt ")
    binary.Write(f, binary.LittleEndian, uint32(16))
    binary.Write(f, binary.LittleEndian, uint16(1))
    binary.Write(f, binary.LittleEndian, numChannels)
    binary.Write(f, binary.LittleEndian, sampleRate)
    binary.Write(f, binary.LittleEndian, byteRate)
    binary.Write(f, binary.LittleEndian, blockAlign)
    binary.Write(f, binary.LittleEndian, bitsPerSample)
    f.WriteString("data")
    binary.Write(f, binary.LittleEndian, dataSize)
    _, err = f.Write(pcmData)
    return err
}

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    generationConfig := &interactions.GenerationConfig{
        SpeechConfig: genai.Ptr(interactions.NewSpeechConfigUnion([]interactions.SpeechConfig{
            {Voice: genai.Ptr("Kore")},
        })),
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.1-flash-tts-preview"),
            Input: interactions.NewInteractionsInput("Say cheerfully: Have a wonderful day!"),
            ResponseFormat: genai.Ptr(interactions.NewCreateModelInteractionResponseFormat(
                interactions.NewResponseFormat(interactions.AudioResponseFormat{}),
            )),
            GenerationConfig: generationConfig,
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    if res.Interaction.OutputAudio != nil && res.Interaction.OutputAudio.Data != nil {
        pcmBytes, err := base64.StdEncoding.DecodeString(*res.Interaction.OutputAudio.Data)
        if err != nil {
            log.Fatal(err)
        }
        if err := saveWaveFile("out.wav", pcmBytes); err != nil {
            log.Fatal(err)
        }
    }
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash-tts",
    "input": [{
      "type": "user_input",
      "content": [{
        "type": "text",
        "text": "Have a wonderful day!",
        "annotations": [{
          "type": "speech_metadata",
          "style": "cheerful and friendly"
        }]
      }]
    }],
    "response_format": {
      "type": "audio"
    },
    "generation_config": {
      "speech_config": [
        { "voice": "Kore" }
      ]
    }
  }' | jq -r '[.steps[] | select(.type=="model_output") | .content[] | select(.type=="audio")] | last | .data' | base64 --decode > out.wav

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash-tts",
    input=[{
        "type": "user_input",
        "content": [
            {
                "type": "text",
                "text": "How's it going today Jane?",
                "annotations": [{
                    "type": "speech_metadata",
                    "speaker": "Joe",
                    "style": "cheerful and friendly",
                }],
            },
            {
                "type": "text",
                "text": "Not too bad, how about you? Ready to test these new voices?",
                "annotations": [{
                    "type": "speech_metadata",
                    "speaker": "Jane",
                    "style": "calm and relaxed",
                }],
            },
        ],
    }],
    response_format={"type": "audio"},
    generation_config={
        "speech_config": {
            "mode": "conversational",
            "speakers": [
                {"speaker": "Joe", "voice": "Puck"},
                {"speaker": "Jane", "voice": "Kore"},
            ],
        }
    },
)

with open("out.wav", "wb") as f:
    f.write(base64.b64decode(interaction.output_audio.data))

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

async function main() {
   const client = new GoogleGenAI({});

   const interaction = await client.interactions.create({
      model: 'gemini-3.8-flash-tts',
      input: [{
         type: 'user_input',
         content: [
            {
               type: 'text',
               text: "How's it going today Jane?",
               annotations: [{
                  type: 'speech_metadata',
                  speaker: 'Joe',
                  style: 'cheerful and friendly',
               }],
            },
            {
               type: 'text',
               text: 'Not too bad, how about you? Ready to test these new voices?',
               annotations: [{
                  type: 'speech_metadata',
                  speaker: 'Jane',
                  style: 'calm and relaxed',
               }],
            },
         ],
      }],
      response_format: { type: 'audio' },
      generation_config: {
         speech_config: {
            mode: 'conversational',
            speakers: [
               { speaker: 'Joe', voice: 'Puck' },
               { speaker: 'Jane', voice: 'Kore' },
            ],
         },
      },
   });

   const audioBuffer = Buffer.from(interaction.output_audio.data, 'base64');
   fs.writeFileSync('out.wav', audioBuffer);
}

await main();

package main

import (
    "context"
    "encoding/base64"
    "encoding/binary"
    "log"
    "os"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func saveWaveFile(filename string, pcmData []byte) error {
    f, err := os.Create(filename)
    if err != nil {
        return err
    }
    defer f.Close()

    sampleRate := uint32(24000)
    numChannels := uint16(1)
    bitsPerSample := uint16(16)
    byteRate := sampleRate * uint32(numChannels) * uint32(bitsPerSample/8)
    blockAlign := numChannels * (bitsPerSample / 8)
    dataSize := uint32(len(pcmData))

    f.WriteString("RIFF")
    binary.Write(f, binary.LittleEndian, uint32(36+dataSize))
    f.WriteString("WAVEfmt ")
    binary.Write(f, binary.LittleEndian, uint32(16))
    binary.Write(f, binary.LittleEndian, uint16(1))
    binary.Write(f, binary.LittleEndian, numChannels)
    binary.Write(f, binary.LittleEndian, sampleRate)
    binary.Write(f, binary.LittleEndian, byteRate)
    binary.Write(f, binary.LittleEndian, blockAlign)
    binary.Write(f, binary.LittleEndian, bitsPerSample)
    f.WriteString("data")
    binary.Write(f, binary.LittleEndian, dataSize)
    _, err = f.Write(pcmData)
    return err
}

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    prompt := "TTS the following conversation between Joe and Jane:\n" +
        "Joe: How's it going today Jane?\n" +
        "Jane: Not too bad, how about you?"

    generationConfig := &interactions.GenerationConfig{
        SpeechConfig: genai.Ptr(interactions.NewSpeechConfigUnion([]interactions.SpeechConfig{
            {Speaker: genai.Ptr("Joe"), Voice: genai.Ptr("Kore")},
            {Speaker: genai.Ptr("Jane"), Voice: genai.Ptr("Puck")},
        })),
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.1-flash-tts-preview"),
            Input: interactions.NewInteractionsInput(prompt),
            ResponseFormat: genai.Ptr(interactions.NewCreateModelInteractionResponseFormat(
                interactions.NewResponseFormat(interactions.AudioResponseFormat{}),
            )),
            GenerationConfig: generationConfig,
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    if res.Interaction.OutputAudio != nil && res.Interaction.OutputAudio.Data != nil {
        pcmBytes, err := base64.StdEncoding.DecodeString(*res.Interaction.OutputAudio.Data)
        if err != nil {
            log.Fatal(err)
        }
        if err := saveWaveFile("out.wav", pcmBytes); err != nil {
            log.Fatal(err)
        }
    }
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash-tts",
    "input": [{
      "type": "user_input",
      "content": [
        {
          "type": "text",
          "text": "How'\''s it going today Jane?",
          "annotations": [{
            "type": "speech_metadata",
            "speaker": "Joe",
            "style": "cheerful and friendly"
          }]
        },
        {
          "type": "text",
          "text": "Not too bad, how about you? Ready to test these new voices?",
          "annotations": [{
            "type": "speech_metadata",
            "speaker": "Jane",
            "style": "calm and relaxed"
          }]
        }
      ]
    }],
    "response_format": {
      "type": "audio"
    },
    "generation_config": {
      "speech_config": {
        "mode": "conversational",
        "speakers": [
          { "speaker": "Joe", "voice": "Puck" },
          { "speaker": "Jane", "voice": "Kore" }
        ]
      }
    }
  }'

package main

import (
    "context"
    "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)
    }

    transcriptRes, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput(
                "Generate a short transcript around 100 words that reads " +
                    "like it was clipped from a podcast by excited herpetologists. " +
                    "The hosts names are Dr. Anya and Liam.",
            ),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    var transcript string
    if transcriptRes.Interaction.OutputText != nil {
        transcript = *transcriptRes.Interaction.OutputText
    }

    generationConfig := &interactions.GenerationConfig{
        SpeechConfig: genai.Ptr(interactions.NewSpeechConfigUnion([]interactions.SpeechConfig{
            {Speaker: genai.Ptr("Dr. Anya"), Voice: genai.Ptr("Kore")},
            {Speaker: genai.Ptr("Liam"), Voice: genai.Ptr("Puck")},
        })),
    }

    ttsRes, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.1-flash-tts-preview"),
            Input: interactions.NewInteractionsInput(transcript),
            ResponseFormat: genai.Ptr(interactions.NewCreateModelInteractionResponseFormat(
                interactions.NewResponseFormat(interactions.AudioResponseFormat{}),
            )),
            GenerationConfig: generationConfig,
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    _ = ttsRes
}

import base64
from google import genai

client = genai.Client()

stream = client.interactions.create(
    model="gemini-3.8-flash-tts",
    input=[{
        "type": "user_input",
        "content": [{
            "type": "text",
            "text": "Have a wonderful day!",
            "annotations": [{
                "type": "speech_metadata",
                "style": "cheerful and friendly",
            }],
        }],
    }],
    response_format={"type": "audio"},
    generation_config={
        "speech_config": [
            {"voice": "Kore"},
        ]
    },
    stream=True,
)

for event in stream:
    if event.event_type == "step.delta":
        if event.delta.type == "audio":
            audio_data = base64.b64decode(event.delta.data)
            # Process the audio chunk (e.g. play it or write to a file)

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

async function main() {
   const client = new GoogleGenAI({});

   const stream = await client.interactions.create({
      model: 'gemini-3.8-flash-tts',
      input: [{
         type: 'user_input',
         content: [{
            type: 'text',
            text: 'Have a wonderful day!',
            annotations: [{
               type: 'speech_metadata',
               style: 'cheerful and friendly',
            }],
         }],
      }],
      response_format: { type: 'audio' },
      generation_config: {
         speech_config: [
            { voice: 'Kore' },
         ],
      },
      stream: true,
   });

   for await (const event of stream) {
      if (event.event_type === 'step.delta') {
         if (event.delta.type === 'audio') {
            const audioBuffer = Buffer.from(event.delta.data, 'base64');
            // Process the audio buffer
         }
      }
   }
}
await main();

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  --no-buffer \
  -d '{
    "model": "gemini-3.8-flash-tts",
    "input": [{
      "type": "user_input",
      "content": [{
        "type": "text",
        "text": "Have a wonderful day!",
        "annotations": [{
          "type": "speech_metadata",
          "style": "cheerful and friendly"
        }]
      }]
    }],
    "response_format": {
      "type": "audio"
    },
    "generation_config": {
      "speech_config": [
        { "voice": "Kore" }
      ]
    },
    "stream": true
  }'

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash-tts",
    input=[{
        "type": "user_input",
        "content": [{
            "type": "text",
            "text": "Have a wonderful day!",
            "annotations": [{
                "type": "speech_metadata",
                "style": "cheerful and friendly",
            }],
        }],
    }],
    response_format={
        "type": "audio",
        "mime_type": "audio/l16",  # "audio/wav" (default), "audio/l16", "audio/mulaw", or "audio/alaw"
        "sample_rate": 24000,
    },
    generation_config={
        "speech_config": [
            {"voice": "Kore"},
        ]
    },
)

with open("out.pcm", "wb") as f:
    f.write(base64.b64decode(interaction.output_audio.data))

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

async function main() {
   const client = new GoogleGenAI({});

   const interaction = await client.interactions.create({
      model: 'gemini-3.8-flash-tts',
      input: [{
         type: 'user_input',
         content: [{
            type: 'text',
            text: 'Have a wonderful day!',
            annotations: [{
               type: 'speech_metadata',
               style: 'cheerful and friendly',
            }],
         }],
      }],
      response_format: {
         type: 'audio',
         mime_type: 'audio/l16', // 'audio/wav' (default), 'audio/l16', 'audio/mulaw', or 'audio/alaw'
         sample_rate: 24000,
      },
      generation_config: {
         speech_config: [
            { voice: 'Kore' },
         ],
      },
   });

   const audioBuffer = Buffer.from(interaction.output_audio.data, 'base64');
   fs.writeFileSync('out.pcm', audioBuffer);
}
await main();

package main

import (
    "context"
    "encoding/base64"
    "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)
    }

    generationConfig := &interactions.GenerationConfig{
        SpeechConfig: genai.Ptr(interactions.NewSpeechConfigUnion([]interactions.SpeechConfig{
            {Voice: genai.Ptr("Kore")},
        })),
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.1-flash-tts-preview"),
            Input: interactions.NewInteractionsInput("Say cheerfully: Have a wonderful day!"),
            ResponseFormat: genai.Ptr(interactions.NewCreateModelInteractionResponseFormat(
                interactions.NewResponseFormat(interactions.AudioResponseFormat{}),
            )),
            GenerationConfig: generationConfig,
            Stream:           genai.Ptr(true),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    stream := res.InteractionSSEStreamEvent
    defer stream.Close()

    for stream.Next() {
        event := stream.Value()
        if stepDelta := event.GetDataStepDelta(); stepDelta != nil {
            if audioDelta := stepDelta.GetDeltaAudio(); audioDelta != nil && audioDelta.Data != nil {
                audioData, err := base64.StdEncoding.DecodeString(*audioDelta.Data)
                if err != nil {
                    log.Fatal(err)
                }
                // Process the audio chunk (e.g. play it or write to a file)
                _ = audioData
            }
        }
    }
    if err := stream.Err(); err != nil {
        log.Fatal(err)
    }
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash-tts",
    "input": [{
      "type": "user_input",
      "content": [{
        "type": "text",
        "text": "Have a wonderful day!",
        "annotations": [{
          "type": "speech_metadata",
          "style": "cheerful and friendly"
        }]
      }]
    }],
    "response_format": {
      "type": "audio",
      "mime_type": "audio/l16",
      "sample_rate": 24000
    },
    "generation_config": {
      "speech_config": [
        { "voice": "Kore" }
      ]
    }
  }'

from google import genai

client = genai.Client()

# Filter the Voice Library by language, gender, pitch, domain context, and keyword
response = client.voices.list(
    language_code=["en-US", "en-GB"],
    gender=["female"],
    pitch=["medium", "low"],
    contexts=["Audiobook", "Conversational"],
    type_=["prebuilt"],
    search="warm",
    page_size=50,
)

for voice in response.voices or []:
    print(
        f"{voice.id} | {voice.display_name} ({voice.language_code},"
        f" {voice.accent}, {voice.gender}, pitch={voice.pitch}):"
        f" {voice.description}"
    )

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

const ai = new GoogleGenAI();

// Filter the Voice Library by language, gender, pitch, domain context, and keyword
const response = await ai.voices.list({
  language_code: ["en-US", "en-GB"],
  gender: ["female"],
  pitch: ["medium", "low"],
  contexts: ["Audiobook", "Conversational"],
  type: ["prebuilt"],
  search: "warm",
  page_size: 50,
});

for (const voice of response.voices ?? []) {
  console.log(
    `${voice.id} | ${voice.display_name} (${voice.language_code}, ${voice.accent}, ${voice.gender}, pitch=${voice.pitch}): ${voice.description}`
  );
}

curl -G "https://generativelanguage.googleapis.com/v1beta/voices" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  --data-urlencode "language_code=en-US" \
  --data-urlencode "language_code=en-GB" \
  --data-urlencode "gender=female" \
  --data-urlencode "pitch=medium" \
  --data-urlencode "context=Audiobook" \
  --data-urlencode "type=prebuilt" \
  --data-urlencode "search=warm" \
  --data-urlencode "page_size=50"

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash-tts",
    input=[{
        "type": "user_input",
        "content": [{
            "type": "text",
            "text": "Have a wonderful day!",
            "annotations": [{
                "type": "speech_metadata",
                "style": "cheerful and friendly",
            }],
        }],
    }],
    response_format={"type": "audio"},
    generation_config={
        "speech_config": [
            {"voice": "Kore"},
        ]
    },
)

with open("out.wav", "wb") as f:
    f.write(base64.b64decode(interaction.output_audio.data))

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

async function main() {
   const client = new GoogleGenAI({});

   const interaction = await client.interactions.create({
      model: 'gemini-3.8-flash-tts',
      input: [{
         type: 'user_input',
         content: [{
            type: 'text',
            text: 'Have a wonderful day!',
            annotations: [{
               type: 'speech_metadata',
               style: 'cheerful and friendly',
            }],
         }],
      }],
      response_format: { type: 'audio' },
      generation_config: {
         speech_config: [
            { voice: 'Kore' },
         ],
      },
   });

   const audioBuffer = Buffer.from(interaction.output_audio.data, 'base64');
   fs.writeFileSync('out.wav', audioBuffer);
}
await main();

package main

import (
    "context"
    "encoding/base64"
    "encoding/binary"
    "log"
    "os"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func saveWaveFile(filename string, pcmData []byte) error {
    f, err := os.Create(filename)
    if err != nil {
        return err
    }
    defer f.Close()

    sampleRate := uint32(24000)
    numChannels := uint16(1)
    bitsPerSample := uint16(16)
    byteRate := sampleRate * uint32(numChannels) * uint32(bitsPerSample/8)
    blockAlign := numChannels * (bitsPerSample / 8)
    dataSize := uint32(len(pcmData))

    f.WriteString("RIFF")
    binary.Write(f, binary.LittleEndian, uint32(36+dataSize))
    f.WriteString("WAVEfmt ")
    binary.Write(f, binary.LittleEndian, uint32(16))
    binary.Write(f, binary.LittleEndian, uint16(1))
    binary.Write(f, binary.LittleEndian, numChannels)
    binary.Write(f, binary.LittleEndian, sampleRate)
    binary.Write(f, binary.LittleEndian, byteRate)
    binary.Write(f, binary.LittleEndian, blockAlign)
    binary.Write(f, binary.LittleEndian, bitsPerSample)
    f.WriteString("data")
    binary.Write(f, binary.LittleEndian, dataSize)
    _, err = f.Write(pcmData)
    return err
}

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    generationConfig := &interactions.GenerationConfig{
        SpeechConfig: genai.Ptr(interactions.NewSpeechConfigUnion([]interactions.SpeechConfig{
            {Voice: genai.Ptr("Kore")},
        })),
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.1-flash-tts-preview"),
            Input: interactions.NewInteractionsInput("Say cheerfully: Have a wonderful day!"),
            ResponseFormat: genai.Ptr(interactions.NewCreateModelInteractionResponseFormat(
                interactions.NewResponseFormat(interactions.AudioResponseFormat{}),
            )),
            GenerationConfig: generationConfig,
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    if res.Interaction.OutputAudio != nil && res.Interaction.OutputAudio.Data != nil {
        pcmBytes, err := base64.StdEncoding.DecodeString(*res.Interaction.OutputAudio.Data)
        if err != nil {
            log.Fatal(err)
        }
        if err := saveWaveFile("out.wav", pcmBytes); err != nil {
            log.Fatal(err)
        }
    }
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash-tts",
    "input": [{
      "type": "user_input",
      "content": [{
        "type": "text",
        "text": "Have a wonderful day!",
        "annotations": [{
          "type": "speech_metadata",
          "style": "cheerful and friendly"
        }]
      }]
    }],
    "response_format": {
      "type": "audio"
    },
    "generation_config": {
      "speech_config": [
        { "voice": "Kore" }
      ]
    }
  }' | jq -r '[.steps[] | select(.type=="model_output") | .content[] | select(.type=="audio")] | last | .data' | base64 --decode > out.wav

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash-tts",
    input=[{
        "type": "user_input",
        "content": [
            {
                "type": "text",
                "text": "How's it going today Jane?",
                "annotations": [{
                    "type": "speech_metadata",
                    "speaker": "Joe",
                    "style": "cheerful and friendly",
                }],
            },
            {
                "type": "text",
                "text": "Not too bad, how about you? Ready to test these new voices?",
                "annotations": [{
                    "type": "speech_metadata",
                    "speaker": "Jane",
                    "style": "calm and relaxed",
                }],
            },
        ],
    }],
    response_format={"type": "audio"},
    generation_config={
        "speech_config": {
            "mode": "conversational",
            "speakers": [
                {"speaker": "Joe", "voice": "Puck"},
                {"speaker": "Jane", "voice": "Kore"},
            ],
        }
    },
)

with open("out.wav", "wb") as f:
    f.write(base64.b64decode(interaction.output_audio.data))

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

async function main() {
   const client = new GoogleGenAI({});

   const interaction = await client.interactions.create({
      model: 'gemini-3.8-flash-tts',
      input: [{
         type: 'user_input',
         content: [
            {
               type: 'text',
               text: "How's it going today Jane?",
               annotations: [{
                  type: 'speech_metadata',
                  speaker: 'Joe',
                  style: 'cheerful and friendly',
               }],
            },
            {
               type: 'text',
               text: 'Not too bad, how about you? Ready to test these new voices?',
               annotations: [{
                  type: 'speech_metadata',
                  speaker: 'Jane',
                  style: 'calm and relaxed',
               }],
            },
         ],
      }],
      response_format: { type: 'audio' },
      generation_config: {
         speech_config: {
            mode: 'conversational',
            speakers: [
               { speaker: 'Joe', voice: 'Puck' },
               { speaker: 'Jane', voice: 'Kore' },
            ],
         },
      },
   });

   const audioBuffer = Buffer.from(interaction.output_audio.data, 'base64');
   fs.writeFileSync('out.wav', audioBuffer);
}

await main();

package main

import (
    "context"
    "encoding/base64"
    "encoding/binary"
    "log"
    "os"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func saveWaveFile(filename string, pcmData []byte) error {
    f, err := os.Create(filename)
    if err != nil {
        return err
    }
    defer f.Close()

    sampleRate := uint32(24000)
    numChannels := uint16(1)
    bitsPerSample := uint16(16)
    byteRate := sampleRate * uint32(numChannels) * uint32(bitsPerSample/8)
    blockAlign := numChannels * (bitsPerSample / 8)
    dataSize := uint32(len(pcmData))

    f.WriteString("RIFF")
    binary.Write(f, binary.LittleEndian, uint32(36+dataSize))
    f.WriteString("WAVEfmt ")
    binary.Write(f, binary.LittleEndian, uint32(16))
    binary.Write(f, binary.LittleEndian, uint16(1))
    binary.Write(f, binary.LittleEndian, numChannels)
    binary.Write(f, binary.LittleEndian, sampleRate)
    binary.Write(f, binary.LittleEndian, byteRate)
    binary.Write(f, binary.LittleEndian, blockAlign)
    binary.Write(f, binary.LittleEndian, bitsPerSample)
    f.WriteString("data")
    binary.Write(f, binary.LittleEndian, dataSize)
    _, err = f.Write(pcmData)
    return err
}

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    prompt := "TTS the following conversation between Joe and Jane:\n" +
        "Joe: How's it going today Jane?\n" +
        "Jane: Not too bad, how about you?"

    generationConfig := &interactions.GenerationConfig{
        SpeechConfig: genai.Ptr(interactions.NewSpeechConfigUnion([]interactions.SpeechConfig{
            {Speaker: genai.Ptr("Joe"), Voice: genai.Ptr("Kore")},
            {Speaker: genai.Ptr("Jane"), Voice: genai.Ptr("Puck")},
        })),
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.1-flash-tts-preview"),
            Input: interactions.NewInteractionsInput(prompt),
            ResponseFormat: genai.Ptr(interactions.NewCreateModelInteractionResponseFormat(
                interactions.NewResponseFormat(interactions.AudioResponseFormat{}),
            )),
            GenerationConfig: generationConfig,
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    if res.Interaction.OutputAudio != nil && res.Interaction.OutputAudio.Data != nil {
        pcmBytes, err := base64.StdEncoding.DecodeString(*res.Interaction.OutputAudio.Data)
        if err != nil {
            log.Fatal(err)
        }
        if err := saveWaveFile("out.wav", pcmBytes); err != nil {
            log.Fatal(err)
        }
    }
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash-tts",
    "input": [{
      "type": "user_input",
      "content": [
        {
          "type": "text",
          "text": "How'\''s it going today Jane?",
          "annotations": [{
            "type": "speech_metadata",
            "speaker": "Joe",
            "style": "cheerful and friendly"
          }]
        },
        {
          "type": "text",
          "text": "Not too bad, how about you? Ready to test these new voices?",
          "annotations": [{
            "type": "speech_metadata",
            "speaker": "Jane",
            "style": "calm and relaxed"
          }]
        }
      ]
    }],
    "response_format": {
      "type": "audio"
    },
    "generation_config": {
      "speech_config": {
        "mode": "conversational",
        "speakers": [
          { "speaker": "Joe", "voice": "Puck" },
          { "speaker": "Jane", "voice": "Kore" }
        ]
      }
    }
  }'

package main

import (
    "context"
    "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)
    }

    transcriptRes, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput(
                "Generate a short transcript around 100 words that reads " +
                    "like it was clipped from a podcast by excited herpetologists. " +
                    "The hosts names are Dr. Anya and Liam.",
            ),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    var transcript string
    if transcriptRes.Interaction.OutputText != nil {
        transcript = *transcriptRes.Interaction.OutputText
    }

    generationConfig := &interactions.GenerationConfig{
        SpeechConfig: genai.Ptr(interactions.NewSpeechConfigUnion([]interactions.SpeechConfig{
            {Speaker: genai.Ptr("Dr. Anya"), Voice: genai.Ptr("Kore")},
            {Speaker: genai.Ptr("Liam"), Voice: genai.Ptr("Puck")},
        })),
    }

    ttsRes, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.1-flash-tts-preview"),
            Input: interactions.NewInteractionsInput(transcript),
            ResponseFormat: genai.Ptr(interactions.NewCreateModelInteractionResponseFormat(
                interactions.NewResponseFormat(interactions.AudioResponseFormat{}),
            )),
            GenerationConfig: generationConfig,
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    _ = ttsRes
}