Gemini 3.8 Flash-Lite TTS

from google import genai

client = genai.Client(enterprise=True, project="PROJECT_ID", location="global")

response = client.models.generate_content(
    model="gemini-3.8-flash-lite-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"}},
    },
)

# The SDK has already decoded the base64 audio, so inline_data.data is a
# complete WAV file by default.
with open("out.wav", "wb") as f:
    f.write(response.candidates[0].content.parts[0].inline_data.data)

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/google/models/gemini-3.8-flash-lite-tts:generateContent \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [{
        "text": "Have a wonderful day!",
        "speechMetadata": {"style": "cheerful and friendly"}
      }]
    }],
    "generationConfig": {
      "responseModalities": ["AUDIO"],
      "speechConfig": {
        "voiceConfig": {"voice": "Kore"}
      }
    }
  }' | jq -r '.candidates[0].content.parts[0].inlineData.data' | base64 --decode > out.wav