What is the Gemini API's text-to-speech capability and how do you use it?

from google import genai
from google.genai import types
import wave

client = genai.Client()

# Single-speaker TTS:
response = client.models.generate_content(
    model="gemini-3.1-flash-tts-preview",
    contents="Welcome to the Gemini API tutorial. Today we explore text-to-speech.",
    config=types.GenerateContentConfig(
        response_modalities=["AUDIO"],
        speech_config=types.SpeechConfig(
            voice_config=types.VoiceConfig(
                prebuilt_voice_config=types.PrebuiltVoiceConfig(
                    voice_name="Aoede"   # one of 30 available voices
                )
            )
        )
    )
)
# Extract and save audio:
audio_data = response.candidates[0].content.parts[0].inline_data.data
with open("output.wav", "wb") as f:
    f.write(audio_data)

# Multi-speaker TTS (new in 2026):
response = client.models.generate_content(
    model="gemini-3.1-flash-tts-preview",
    contents="""TTS the following conversation:
    <speaker name="Narrator">The story begins on a dark night.</speaker>
    <speaker name="Alice">Who goes there?</speaker>
    <speaker name="Bob">It is I, your long-lost friend!</speaker>
    """,
    config=types.GenerateContentConfig(
        response_modalities=["AUDIO"],
        speech_config=types.SpeechConfig(
            multi_speaker_voice_config=types.MultiSpeakerVoiceConfig(
                speaker_voice_configs=[
                    types.SpeakerVoiceConfig(speaker="Alice", voice_config=types.VoiceConfig(
                        prebuilt_voice_config=types.PrebuiltVoiceConfig(voice_name="Aoede")
                    )),
                    types.SpeakerVoiceConfig(speaker="Bob", voice_config=types.VoiceConfig(
                        prebuilt_voice_config=types.PrebuiltVoiceConfig(voice_name="Charon")
                    )),
                ]
            )
        )
    )
)