But with anything OpenAI-like being able to just set the additional parameters JSON would already go a long way.
Opening this issue in case that's lower hanging.
Originally created by @manuhortet on GitHub (Dec 20, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20057
### Problem Description
It is not possible right now to set different configurations for TTS with different models.
### Desired Solution you'd like
This issue discusses the possibility of setting complete model-specific TTS configurations: https://github.com/open-webui/open-webui/issues/3097
But with anything OpenAI-like being able to just set the additional parameters JSON would already go a long way.
Opening this issue in case that's lower hanging.
@owui-terminator[bot] commented on GitHub (Dec 20, 2025):
🔍Similar Issues Found
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
#8354feat: Per-model TTS options by TheRealPSV • Jan 06, 2025
#3097enh: Allow setting TTS voice selection per model by oss001 • Jun 12, 2024 • enhancement, good first issue
#3347feat: Configure TTS voice per Model by chrishart0 • Jun 21, 2024
#19817feat: Ability to specify different task models for different tasks and user groups by Mikikrus • Dec 08, 2025
#12159feat: allow specifying extra model parameters by solesensei • Mar 28, 2025
Show 5 more related issues
#19908feat: Supports OpenAI-Response format API and related parameters by daxiass • Dec 12, 2025
#1978enhancement: Allow selection of OpenAI TTS models by jmtatsch • May 05, 2024
#5408"language" parameter for openai stt by Raigedas • Sep 13, 2024
#19580feat: Please let me disable TTS by PaulKlumpp • Nov 28, 2025
#4834enh: advanced options for TTS integrations by kiosion • Aug 22, 2024
💡Tips:
If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
If you found a solution in any of these issues, please share it here to help others
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
<!-- gh-comment-id:3677778162 -->
@owui-terminator[bot] commented on GitHub (Dec 20, 2025):
🔍 **Similar Issues Found**
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
1. [#8354](https://github.com/open-webui/open-webui/issues/8354) **feat: Per-model TTS options**
*by TheRealPSV • Jan 06, 2025*
2. [#3097](https://github.com/open-webui/open-webui/issues/3097) **enh: Allow setting TTS voice selection per model**
*by oss001 • Jun 12, 2024 • `enhancement`, `good first issue`*
3. [#3347](https://github.com/open-webui/open-webui/issues/3347) **feat: Configure TTS voice per Model**
*by chrishart0 • Jun 21, 2024*
4. [#19817](https://github.com/open-webui/open-webui/issues/19817) **feat: Ability to specify different task models for different tasks and user groups**
*by Mikikrus • Dec 08, 2025*
5. [#12159](https://github.com/open-webui/open-webui/issues/12159) **feat: allow specifying extra model parameters**
*by solesensei • Mar 28, 2025*
<details>
<summary>Show 5 more related issues</summary>
6. [#19908](https://github.com/open-webui/open-webui/issues/19908) **feat: Supports OpenAI-Response format API and related parameters**
*by daxiass • Dec 12, 2025*
7. [#1978](https://github.com/open-webui/open-webui/issues/1978) **enhancement: Allow selection of OpenAI TTS models**
*by jmtatsch • May 05, 2024*
8. [#5408](https://github.com/open-webui/open-webui/issues/5408) **"language" parameter for openai stt**
*by Raigedas • Sep 13, 2024*
9. [#19580](https://github.com/open-webui/open-webui/issues/19580) **feat: Please let me disable TTS**
*by PaulKlumpp • Nov 28, 2025*
10. [#4834](https://github.com/open-webui/open-webui/issues/4834) **enh: advanced options for TTS integrations**
*by kiosion • Aug 22, 2024*
</details>
---
💡 **Tips:**
- If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
- If you found a solution in any of these issues, please share it here to help others
*This comment was generated automatically by a bot.* Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
But with anything OpenAI-like being able to just set the additional parameters JSON would already go a long way.
Opening this issue in case that's lower hanging.
but you can already pass extra parameters in the audio config in the additional parameters field as json?
<!-- gh-comment-id:3677926327 -->
@Classic298 commented on GitHub (Dec 20, 2025):
> But with anything OpenAI-like being able to just set the additional parameters JSON would already go a long way.
> Opening this issue in case that's lower hanging.
but you can already pass extra parameters in the audio config in the additional parameters field as json?
@Classic298 - Not per model, which is what I need. Or am I missing something?
<!-- gh-comment-id:3696510402 -->
@manuhortet commented on GitHub (Dec 29, 2025):
@Classic298 - Not per model, which is what I need. Or am I missing something?
<!-- gh-comment-id:3696545442 -->
@Classic298 commented on GitHub (Dec 29, 2025):
Ah. Per model. I must have only read the issue description.
No per model is not possible currently.
But it seems your issue is a duplicate/extension of https://github.com/open-webui/open-webui/issues/3097 so the discussion should be continued there
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @manuhortet on GitHub (Dec 20, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20057
Problem Description
It is not possible right now to set different configurations for TTS with different models.
Desired Solution you'd like
This issue discusses the possibility of setting complete model-specific TTS configurations: https://github.com/open-webui/open-webui/issues/3097
But with anything OpenAI-like being able to just set the additional parameters JSON would already go a long way.
Opening this issue in case that's lower hanging.
@owui-terminator[bot] commented on GitHub (Dec 20, 2025):
🔍 Similar Issues Found
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
#8354 feat: Per-model TTS options
by TheRealPSV • Jan 06, 2025
#3097 enh: Allow setting TTS voice selection per model
by oss001 • Jun 12, 2024 •
enhancement,good first issue#3347 feat: Configure TTS voice per Model
by chrishart0 • Jun 21, 2024
#19817 feat: Ability to specify different task models for different tasks and user groups
by Mikikrus • Dec 08, 2025
#12159 feat: allow specifying extra model parameters
by solesensei • Mar 28, 2025
Show 5 more related issues
#19908 feat: Supports OpenAI-Response format API and related parameters
by daxiass • Dec 12, 2025
#1978 enhancement: Allow selection of OpenAI TTS models
by jmtatsch • May 05, 2024
#5408 "language" parameter for openai stt
by Raigedas • Sep 13, 2024
#19580 feat: Please let me disable TTS
by PaulKlumpp • Nov 28, 2025
#4834 enh: advanced options for TTS integrations
by kiosion • Aug 22, 2024
💡 Tips:
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
@Classic298 commented on GitHub (Dec 20, 2025):
but you can already pass extra parameters in the audio config in the additional parameters field as json?
@manuhortet commented on GitHub (Dec 29, 2025):
@Classic298 - Not per model, which is what I need. Or am I missing something?
@Classic298 commented on GitHub (Dec 29, 2025):
Ah. Per model. I must have only read the issue description.
No per model is not possible currently.
But it seems your issue is a duplicate/extension of https://github.com/open-webui/open-webui/issues/3097 so the discussion should be continued there