Audio generation using gemini tts modals

General
, ,
1

i tried but im getting errors also i cant find any example for googles tts modals. in cookbook or in agno docs.

import base64

import requests
from agno.agent import Agent
from agno.media import Audio
from agno.models.google import Gemini
from agno.utils.audio import write_audio_to_file
from dotenv import load_dotenv

load_dotenv()

# Fetch the audio file and convert it to a base64 encoded string
url = "https://openaiassets.blob.core.windows.net/$web/API/docs/audio/alloy.wav"
response = requests.get(url)
response.raise_for_status()
wav_data = response.content

agent = Agent(
    model=Gemini(
        id="gemini-2.5-flash-preview-tts",
        speech_config="Kore"
    ),
    markdown=True,
)

agent.run("What's in these recording?", audio=[Audio(content=wav_data, format="wav")])

if agent.run_response.response_audio is not None:
    write_audio_to_file(
        audio=agent.run_response.response_audio.content, filename="tmp/result.wav"
    )

i also tried this “response_modalities=[“text”, “audio”],“ parameter but for gemini it only has text and image i think. and “speech_config={“voice”: “Kore”, “format”: “wav”},“ “audio={“voice”: “Kore”, “format”: “wav”},“ this parameters also wont work.

2

Hi @Prajwal, thanks for reaching out and supporting Agno. I’ve shared this with the team, we’re working through all requests one by one and will get back to you soon.If it’s urgent, please let us know. We appreciate your patience!

3

Hey @Prajwal! We are adding support for TTS models soon. Will send updates here

1 Like
4

Hey @Prajwal ! We added support for TTS and it’ll be released in our next release