Text-to-speech `mp3` output format support

[DanieleMorotti]

Hi, I'm currently using the Gemini text-to-speech models and would like to know if it's possible to specify the output format as MP3.

According to the Google Cloud documentation (https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=it#gemini-2-5-pro-tts
), it seems that MP3 output should be supported. However, I haven't been able to find a way to configure the output format using this package.

Is there currently a way to specify the output format (e.g. MP3)? If not, is this feature planned for a future release?

Thank you!

[janasangeetha]

Hi @DanieleMorotti
Thanks for reaching out!
Kindly use below config for MP3 output file:

audio_config=texttospeech.AudioConfig(
        audio_encoding=texttospeech.AudioEncoding.MP3
    )

Reference

[DanieleMorotti]

Sorry for the confusion in my earlier question. I meant to ask whether this is possible with the google-genai package. It doesn't seem so, but I’m wondering why, given that it’s supported in the other package.