テキスト読み上げ生成（TTS）

from google import genai
import wave

def wave_file(filename, pcm, channels=1, rate=24000, sample_width=2):
    with wave.open(filename, "wb") as wf:
        wf.setnchannels(channels)
        wf.setsampwidth(sample_width)
        wf.setframerate(rate)
        wf.writeframes(pcm)

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-tts-preview",
    input="Say cheerfully: Have a wonderful day!",
    response_modalities=["audio"],
    speech_config=[
        {"voice": "Kore"}
    ]
)

data = None
for step in interaction.steps:
    for content_block in step.content:
        if content_block.type == "audio":
            data = content_block.data
            break
    if data:
        break
wave_file('out.wav', data)

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

async function saveWaveFile(
   filename,
   pcmData,
   channels = 1,
   rate = 24000,
   sampleWidth = 2,
) {
   return new Promise((resolve, reject) => {
      const writer = new wav.FileWriter(filename, {
            channels,
            sampleRate: rate,
            bitDepth: sampleWidth * 8,
      });

      writer.on('finish', resolve);
      writer.on('error', reject);

      writer.write(pcmData);
      writer.end();
   });
}

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

   const interaction = await client.interactions.create({
      model: "gemini-3.1-flash-tts-preview",
      input: "Say cheerfully: Have a wonderful day!",
      response_modalities: ['audio'],
      speech_config: [
         { voice: 'Kore' }
      ],
   });

   let data = null;
   for (const step of interaction.steps) {
      for (const contentBlock of step.content) {
         if (contentBlock.type === 'audio') {
            data = contentBlock.data;
            break;
         }
      }
      if (data) break;
   }
   const audioBuffer = Buffer.from(data, 'base64');
   await saveWaveFile('out.wav', audioBuffer);
}
await main();

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-3.1-flash-tts-preview",
    "input": "Say cheerfully: Have a wonderful day!",
    "response_modalities": ["audio"],
    "speech_config": [
      { "voice": "Kore" }
    ]
  }'

from google import genai
import wave

def wave_file(filename, pcm, channels=1, rate=24000, sample_width=2):
   with wave.open(filename, "wb") as wf:
      wf.setnchannels(channels)
      wf.setsampwidth(sample_width)
      wf.setframerate(rate)
      wf.writeframes(pcm)

client = genai.Client()

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

 interaction = client.interactions.create(
     model="gemini-3.1-flash-tts-preview",
     input=prompt,
     response_modalities=["audio"],
     speech_config=[
         {"speaker": "Joe", "voice": "Kore"},
         {"speaker": "Jane", "voice": "Puck"}
     ]
 )

data = None
for step in interaction.steps:
   for content_block in step.content:
      if content_block.type == "audio":
         data = content_block.data
         break
   if data:
      break
wave_file('out.wav', data)

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

async function saveWaveFile(
   filename,
   pcmData,
   channels = 1,
   rate = 24000,
   sampleWidth = 2,
) {
   return new Promise((resolve, reject) => {
      const writer = new wav.FileWriter(filename, {
            channels,
            sampleRate: rate,
            bitDepth: sampleWidth * 8,
      });

      writer.on('finish', resolve);
      writer.on('error', reject);

      writer.write(pcmData);
      writer.end();
   });
}

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

   const prompt = `TTS the following conversation between Joe and Jane:
         Joe: How's it going today Jane?
         Jane: Not too bad, how about you?`;

   const interaction = await client.interactions.create({
      model: "gemini-3.1-flash-tts-preview",
      input: prompt,
      response_modalities: ['audio'],
      speech_config: [
         { speaker: 'Joe', voice: 'Kore' },
         { speaker: 'Jane', voice: 'Puck' }
      ]
   });

   let data = null;
   for (const step of interaction.steps) {
      for (const contentBlock of step.content) {
         if (contentBlock.type === 'audio') {
            data = contentBlock.data;
            break;
         }
      }
      if (data) break;
   }
   const audioBuffer = Buffer.from(data, 'base64');
   await saveWaveFile('out.wav', audioBuffer);
}

await main();

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-3.1-flash-tts-preview",
  "input": "TTS the following conversation between Joe and Jane: Joe: Hows it going today Jane? Jane: Not too bad, how about you?",
  "response_modalities": ["audio"],
  "speech_config": [
    { "speaker": "Joe", "voice": "Kore" },
    { "speaker": "Jane", "voice": "Puck" }
  ]
}'

from google import genai

client = genai.Client()

transcript_interaction = client.interactions.create(
   model="gemini-3-flash-preview",
   input="""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."""
)
transcript = transcript_interaction.steps[-1].content[0].text

tts_interaction = client.interactions.create(
   model="gemini-3.1-flash-tts-preview",
   input=transcript,
   response_modalities=["audio"],
   speech_config=[
      {"speaker": "Dr. Anya", "voice": "Kore"},
      {"speaker": "Liam", "voice": "Puck"}
   ]
)

# ...Code to stream or save the output

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

const client = new GoogleGenAI({});

async function main() {

const transcriptInteraction = await client.interactions.create({
   model: "gemini-3-flash-preview",
   input: "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.",
   })

const ttsInteraction = await client.interactions.create({
   model: "gemini-3.1-flash-tts-preview",
   input: transcriptInteraction.steps.at(-1).content[0].text,
   response_modalities: ['audio'],
   speech_config: [
      { speaker: "Dr. Anya", voice: "Kore" },
      { speaker: "Liam", voice: "Puck" }
   ]
  });
}
// ..JavaScript code for exporting .wav file for output audio

await main();