# Is it allowed to use Gemini TTS output for speaker inversion in another TTS model?

**URL:** <https://discuss.ai.google.dev/t/is-it-allowed-to-use-gemini-tts-output-for-speaker-inversion-in-another-tts-model/188338>\
**Category:** Gemini API\
**Tags:** tts\
**Created:** [October 12, 2026, 3:41am UTC](https://discuss.ai.google.dev/t/is-it-allowed-to-use-gemini-tts-output-for-speaker-inversion-in-another-tts-model/188338 "2026-10-12T03:41:45Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![coffee\_tree](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/coffee_tree/32/156077_2.png) [@coffee\_tree](https://discuss.ai.google.dev/u/coffee_tree)\
**Post date:** [October 12, 2026, 3:41am UTC](https://discuss.ai.google.dev/t/is-it-allowed-to-use-gemini-tts-output-for-speaker-inversion-in-another-tts-model/188338/1 "2026-10-12T03:41:45Z")

</div>

I have a question about the permitted use of audio generated by Gemini TTS.

I am currently using `gemini-2.5-flash-preview-tts` with the Erinome preset voice, and I understand that this is currently a preview model.

I am creating a narrated picture book and I like the voice quality very much. However, in my use case, I sometimes notice variations in speaker tone when generating the narration sentence by sentence.

As a workaround, I am experimenting with Irodori-TTS, an open-source TTS model that supports speaker inversion.

My current experimental workflow is:

1. Generate several short audio samples with `gemini-2.5-flash-preview-tts` using the Erinome preset voice.

2. Use those generated audio samples as reference/training material for Irodori-TTS speaker inversion.

3. Keep the Irodori-TTS base model frozen and train only the speaker embedding / speaker tokens.

4. Use that speaker embedding to generate the narration sentence by sentence with a more consistent speaker tone.

I do not plan to distribute the speaker embedding itself.

If this method works well, I may use the final generated narration audio in a picture book for commercial or non-commercial distribution.

My question is:

Would using audio generated by `gemini-2.5-flash-preview-tts` in this way for speaker inversion in another TTS model violate the Gemini API / Google AI Studio terms, including the restriction related to developing models that compete with the Services?

This is currently only a technical experiment, and I would like to confirm the terms before using the resulting audio in a published work.

Thank you for your help.

---

<div class="post-metadata">

**Author:** ![Mahesh\_Sutar](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/mahesh_sutar/32/31644_2.png) [@Mahesh\_Sutar](https://discuss.ai.google.dev/u/Mahesh_Sutar)\
**Post date:** [October 16, 2026, 10:43am UTC](https://discuss.ai.google.dev/t/is-it-allowed-to-use-gemini-tts-output-for-speaker-inversion-in-another-tts-model/188338/2 "2026-10-16T10:43:57Z")

</div>

Hello @coffee_tree,

We can’t provide specific legal guidance on this forum, including how the terms apply to your speaker inversion workflow.

The competing-models clause sits in [Use Restrictions](https://ai.google.dev/gemini-api/terms#use-restrictions), and [Use of Generated Content](https://ai.google.dev/gemini-api/terms#use-generated) covers the content you generate. Using the Gemini API also requires accepting the [Google APIs Terms of Service](https://developers.google.com/terms).

---

<div class="post-metadata">

**Author:** ![coffee\_tree](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/coffee_tree/32/156077_2.png) [@coffee\_tree](https://discuss.ai.google.dev/u/coffee_tree)\
**Post date:** [October 16, 2026, 2:12pm UTC](https://discuss.ai.google.dev/t/is-it-allowed-to-use-gemini-tts-output-for-speaker-inversion-in-another-tts-model/188338/3 "2026-10-16T14:12:21Z")

</div>

Thank you for your reply and for clarifying the relevant terms.

I understand that this forum cannot provide specific legal guidance.

I have also contacted Google Cloud Sales, but was directed to general technical support and Cloud Partners.

Could you please point me to the appropriate Google team or official channel where I can request written clarification or permission regarding this specific use of Gemini TTS-generated audio?

If no such channel is available for individual developers, I would appreciate knowing that as well.

Thank you for your assistance.
