Skip to main content
"""
Google Text To Speech
=====================

Cookbook example for `google/gemini/text_to_speech.py`.
"""

from agno.agent import Agent
from agno.models.google import Gemini
from agno.utils.audio import write_wav_audio_to_file

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

agent = Agent(
    model=Gemini(
        id="gemini-2.5-flash-preview-tts",
        response_modalities=["AUDIO"],
        speech_config={
            "voice_config": {"prebuilt_voice_config": {"voice_name": "Kore"}}
        },
    )
)

run_output = agent.run("Say cheerfully: Have a wonderful day!")

if run_output.response_audio is not None:
    audio_data = run_output.response_audio.content
    output_file = "tmp/cheerful_greeting.wav"
    write_wav_audio_to_file(output_file, audio_data)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass

​
Run the Example

# Clone and setup repo
git clone https://github.com/agno-agi/agno.git
cd agno/cookbook/90_models/google/gemini

# Create and activate virtual environment
./scripts/demo_setup.sh
source .venvs/demo/bin/activate

python text_to_speech.py