文字转语音生成 (TTS)

from google import genai

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.8-flash-tts",
    contents=[{
        "role": "user",
        "parts": [{
            "text": "Have a wonderful day!",
            "speech_metadata": {"style": "cheerful and friendly"},
        }],
    }],
    config={
        "response_modalities": ["AUDIO"],
        "speech_config": {
            "voice_config": {"voice": "Kore"}
        },
    },
)

data = response.candidates[0].content.parts[0].inline_data.data
with open("out.wav", "wb") as f:
    f.write(data)

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

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

   const response = await ai.models.generateContent({
      model: 'gemini-3.8-flash-tts',
      contents: [{
         role: 'user',
         parts: [{
            text: 'Have a wonderful day!',
            speechMetadata: { style: 'cheerful and friendly' },
         }],
      }],
      config: {
         responseModalities: ['AUDIO'],
         speechConfig: {
            voiceConfig: { voice: 'Kore' },
         },
      },
   });

   const data = response.candidates?.[0]?.content?.parts?.[0]?.inlineData?.data;
   const audioBuffer = Buffer.from(data, 'base64');

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

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.8-flash-tts:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
        "contents": [{
          "role": "user",
          "parts": [{
            "text": "Have a wonderful day!",
            "speech_metadata": {
              "style": "cheerful and friendly"
            }
          }]
        }],
        "generationConfig": {
          "responseModalities": ["AUDIO"],
          "speechConfig": {
            "voiceConfig": {
              "voice": "Kore"
            }
          }
        }
    }' | jq -r '.candidates[0].content.parts[0].inlineData.data' | \
          base64 --decode > out.wav

from google import genai

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.8-flash-tts",
    contents=[{
        "role": "user",
        "parts": [
            {
                "text": "How's it going today Jane?",
                "speech_metadata": {
                    "speaker": "Joe",
                    "style": "cheerful and friendly",
                },
            },
            {
                "text": "Not too bad, how about you? Ready to test these new voices?",
                "speech_metadata": {
                    "speaker": "Jane",
                    "style": "calm and relaxed",
                },
            },
        ],
    }],
    config={
        "response_modalities": ["AUDIO"],
        "speech_config": {
            "multi_speaker_voice_config": {
                "speaker_voice_configs": [
                    {
                        "speaker": "Joe",
                        "voice_config": {
                            "prebuilt_voice_config": {"voice_name": "Puck"}
                        },
                    },
                    {
                        "speaker": "Jane",
                        "voice_config": {
                            "prebuilt_voice_config": {"voice_name": "Kore"}
                        },
                    },
                ]
            }
        },
    },
)

data = response.candidates[0].content.parts[0].inline_data.data
with open("out.wav", "wb") as f:
    f.write(data)

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

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

   const response = await ai.models.generateContent({
      model: 'gemini-3.8-flash-tts',
      contents: [{
         role: 'user',
         parts: [
            {
               text: "How's it going today Jane?",
               speechMetadata: {
                  speaker: 'Joe',
                  style: 'cheerful and friendly',
               },
            },
            {
               text: 'Not too bad, how about you? Ready to test these new voices?',
               speechMetadata: {
                  speaker: 'Jane',
                  style: 'calm and relaxed',
               },
            },
         ],
      }],
      config: {
         responseModalities: ['AUDIO'],
         speechConfig: {
            multiSpeakerVoiceConfig: {
               speakerVoiceConfigs: [
                  {
                     speaker: 'Joe',
                     voiceConfig: {
                        prebuiltVoiceConfig: { voiceName: 'Puck' },
                     },
                  },
                  {
                     speaker: 'Jane',
                     voiceConfig: {
                        prebuiltVoiceConfig: { voiceName: 'Kore' },
                     },
                  },
               ],
            },
         },
      },
   });

   const data = response.candidates?.[0]?.content?.parts?.[0]?.inlineData?.data;
   const audioBuffer = Buffer.from(data, 'base64');

   fs.writeFileSync('out.wav', audioBuffer);
}

await main();

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.8-flash-tts:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [
        {
          "text": "How'\''s it going today Jane?",
          "speech_metadata": {
            "speaker": "Joe",
            "style": "cheerful and friendly"
          }
        },
        {
          "text": "Not too bad, how about you? Ready to test these new voices?",
          "speech_metadata": {
            "speaker": "Jane",
            "style": "calm and relaxed"
          }
        }
      ]
    }],
    "generationConfig": {
      "responseModalities": ["AUDIO"],
      "speechConfig": {
        "multiSpeakerVoiceConfig": {
          "speakerVoiceConfigs": [
            {
              "speaker": "Joe",
              "voiceConfig": {
                "prebuiltVoiceConfig": { "voiceName": "Puck" }
              }
            },
            {
              "speaker": "Jane",
              "voiceConfig": {
                "prebuiltVoiceConfig": { "voiceName": "Kore" }
              }
            }
          ]
        }
      }
    }
  }' | jq -r '.candidates[0].content.parts[0].inlineData.data' | \
      base64 --decode > out.wav

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"

from google import genai

client = genai.Client()

response_stream = client.models.generate_content_stream(
    model="gemini-3.8-flash-tts",
    contents=[{
        "role": "user",
        "parts": [{
            "text": "Have a wonderful day!",
            "speech_metadata": {"style": "cheerful and friendly"},
        }],
    }],
    config={
        "response_modalities": ["AUDIO"],
        "speech_config": {
            "voice_config": {"voice": "Kore"}
        },
    },
)

for chunk in response_stream:
    try:
        data = chunk.candidates[0].content.parts[0].inline_data.data
        # data contains raw PCM bytes (24kHz, 1-channel, 16-bit)
    except (IndexError, AttributeError):
        pass

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

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

   const responseStream = await ai.models.generateContentStream({
      model: 'gemini-3.8-flash-tts',
      contents: [{
         role: 'user',
         parts: [{
            text: 'Have a wonderful day!',
            speechMetadata: { style: 'cheerful and friendly' },
         }],
      }],
      config: {
         responseModalities: ['AUDIO'],
         speechConfig: {
            voiceConfig: { voice: 'Kore' },
         },
      },
   });

   for await (const chunk of responseStream) {
      const data = chunk.candidates?.[0]?.content?.parts?.[0]?.inlineData?.data;
      if (data) {
         const audioBuffer = Buffer.from(data, 'base64');
         // Process the audio buffer
      }
   }
}
await main();

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.8-flash-tts:streamGenerateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
        "contents": [{
          "role": "user",
          "parts": [{
            "text": "Have a wonderful day!",
            "speech_metadata": {
              "style": "cheerful and friendly"
            }
          }]
        }],
        "generationConfig": {
          "responseModalities": ["AUDIO"],
          "speechConfig": {
            "voiceConfig": {
              "voice": "Kore"
            }
          }
        }
    }'

from google import genai

client = genai.Client()

response = client.models.generate_content(
    model="gemini-3.8-flash-tts",
    contents=[{
        "role": "user",
        "parts": [{
            "text": "Have a wonderful day!",
            "speech_metadata": {"style": "cheerful and friendly"},
        }],
    }],
    config={
        "response_modalities": ["AUDIO"],
        "response_format": {
            "audio": {
                "mime_type": "AUDIO_L16",
                "sample_rate": 24000,
            }
        },
        "speech_config": {
            "voice_config": {"voice": "Kore"}
        },
    },
)

data = response.candidates[0].content.parts[0].inline_data.data
with open("out.pcm", "wb") as f:
    f.write(data)

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

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

   const response = await ai.models.generateContent({
      model: 'gemini-3.8-flash-tts',
      contents: [{
         role: 'user',
         parts: [{
            text: 'Have a wonderful day!',
            speechMetadata: { style: 'cheerful and friendly' },
         }],
      }],
      config: {
         responseModalities: ['AUDIO'],
         responseFormat: {
            audio: {
               mimeType: 'AUDIO_L16',
               sampleRate: 24000,
            },
         },
         speechConfig: {
            voiceConfig: { voice: 'Kore' },
         },
      },
   });

   const data = response.candidates?.[0]?.content?.parts?.[0]?.inlineData?.data;
   const audioBuffer = Buffer.from(data, 'base64');

   fs.writeFileSync('out.pcm', audioBuffer);
}
await main();

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.8-flash-tts:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
        "contents": [{
          "role": "user",
          "parts": [{
            "text": "Have a wonderful day!",
            "speech_metadata": {
              "style": "cheerful and friendly"
            }
          }]
        }],
        "generationConfig": {
          "responseModalities": ["AUDIO"],
          "responseFormat": {
            "audio": {
              "mimeType": "AUDIO_L16",
              "sampleRate": 24000
            }
          },
          "speechConfig": {
            "voiceConfig": {
              "voice": "Kore"
            }
          }
        }
    }' | jq -r '.candidates[0].content.parts[0].inlineData.data' | \
          base64 --decode > out.pcm