文字转语音生成 (TTS)

Gemini API 可以使用 Gemini 文字转语音 (TTS) 生成功能将文本输入转换为单个说话者或多个说话者的音频。文字转语音 (TTS) 生成是可控的，这意味着您可以使用自然语言来构建互动，并引导音频的风格、口音、节奏和音调。

TTS 功能不同于通过 Live API 提供的语音生成功能，后者专为交互式非结构化音频以及多模态输入和输出而设计。虽然 Live API 在动态对话上下文中表现出色，但通过 Gemini API 实现的 TTS 专门针对需要精确朗读文本并对风格和声音进行精细控制的场景，例如播客或有声读物生成。

本指南介绍了如何根据文本生成单说话者和多说话者音频。

准备工作

请务必使用具有 Gemini 文字转语音 (TTS) 功能的 Gemini 2.5 模型变体，如支持的模型部分中所列。为了获得最佳效果，请考虑哪种模型最适合您的具体用例。

在开始构建之前，您可能会发现在 AI Studio 中测试 Gemini TTS 模型很有用。

单说话者 TTS

如需将文本转换为单人音频，请将响应模态设置为“音频”，并传递包含语音名称的 speech_config 对象。您需要从预建的输出语音中选择一个语音名称。

此示例将模型生成的输出音频保存到 Wave 文件中：

Python

from google import genai
import wave
import base64

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_format={"type": "audio"},
    generation_config={
        "speech_config": [
            {"voice": "Kore"}
        ]
    }
)

wave_file('out.wav', base64.b64decode(interaction.output_audio.data))

JavaScript

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_format: { type: 'audio' },
      generation_config: {
         speech_config: [
            { voice: 'Kore' }
         ]
      },
    });

   const audioBuffer = Buffer.from(interaction.output_audio.data, 'base64');

   await saveWaveFile('out.wav', audioBuffer);
}
await main();

REST

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_format": {
       "type": "audio"
     },
    "generation_config": {
      "speech_config": [
        { "voice": "Kore" }
      ]
    }
  }'

您可以使用 interaction.output_audio 属性检索生成的音频数据，该属性会返回上次生成的音频块。如需详细了解便捷属性，请参阅互动概览。

多说话人 TTS

对于多扬声器音频，您需要一个 multi_speaker_voice_config 对象，其中每个扬声器（最多 2 个）都配置为 speaker_voice_config。您需要使用提示中使用的相同名称来定义每个 speaker：

Python

from google import genai
import wave
import base64

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_format={"type": "audio"},
     generation_config={
         "speech_config": [
             {"speaker": "Joe", "voice": "Kore"},
             {"speaker": "Jane", "voice": "Puck"}
         ]
     }
 )

wave_file('out.wav', base64.b64decode(interaction.output_audio.data))

JavaScript

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_format: { type: 'audio' },
      generation_config: {
         speech_config: [
            { speaker: 'Joe', voice: 'Kore' },
            { speaker: 'Jane', voice: 'Puck'