SpeechT5 tts, CMU Arctic speaker embeddings #53

New Issue

2026-02-15T17:05:36-05:00

yindo commented

2026-02-15 17:05:36 -05:00

Originally created by @User110112 on GitHub (Dec 18, 2024).

Hello,
I can't get the speecht5 tts option to work properly.
No matter what embedding name (bdl, slt,...) I set there is no change. Only a young woman's voice with much grain, noice in the background.
Am I using wrong embedding names ? Is there something I am not paying attention to ?
Have a great day.

Originally created by @User110112 on GitHub (Dec 18, 2024). Hello, I can't get the speecht5 tts option to work properly. No matter what embedding name (bdl, slt,...) I set there is no change. Only a young woman's voice with much grain, noice in the background. Am I using wrong embedding names ? Is there something I am not paying attention to ? Have a great day.

yindo commented

2026-02-15 17:05:37 -05:00

@silentoplayz commented on GitHub (Dec 18, 2024):

Ensure the voice name has been set in two places:

Settings -> Audio tab:

2: Admin Panel -> Settings -> Audio tab:

I will see about updating the documentation regarding this if this helps you!

@silentoplayz commented on GitHub (Dec 18, 2024): Ensure the voice name has been set in two places: 1. `Settings` -> `Audio` tab: ![image](https://github.com/user-attachments/assets/8942b8a4-9e4d-40ca-8e1a-fb3805f25c6e) 2: `Admin Panel` -> `Settings` -> `Audio` tab: ![image](https://github.com/user-attachments/assets/91bd6caf-f0c4-45f2-bc24-3df94f33dd74) I will see about updating the documentation regarding this if this helps you!

yindo commented

2026-02-15 17:05:38 -05:00

@User110112 commented on GitHub (Dec 19, 2024):

@silentoplayz thank your for the answer. For some reason the voice does not change, no matter what speaker name I use. It's always the woman's voice.
Do you have further recommendations ?

@User110112 commented on GitHub (Dec 19, 2024): @silentoplayz thank your for the answer. For some reason the voice does not change, no matter what speaker name I use. It's always the woman's voice. Do you have further recommendations ?

yindo commented

2026-02-15 17:05:38 -05:00

@richtong commented on GitHub (Jan 3, 2025):

Can't reproduce on 0.5.3 on MacOS running pipx installed though. Seems to work fine with OpenAI

@richtong commented on GitHub (Jan 3, 2025): Can't reproduce on 0.5.3 on MacOS running pipx installed though. Seems to work fine with OpenAI

yindo commented

2026-02-15 17:05:38 -05:00

@orrinwitt commented on GitHub (Feb 8, 2025):

I'm having the same issue, and I think @User110112 is referring to the voices available when using the local (transformers) TTS

@orrinwitt commented on GitHub (Feb 8, 2025): I'm having the same issue, and I think @User110112 is referring to the voices available when using the local (transformers) TTS

yindo commented

2026-02-15 17:05:39 -05:00

@ItsJustRuby commented on GitHub (May 26, 2025):

Specifying the full name of the dataset as TTS Model worked for me, e.g. cmu_us_clb_arctic-wav-arctic_a0001.

@ItsJustRuby commented on GitHub (May 26, 2025): Specifying the full name of the `dataset` as TTS Model worked for me, e.g. `cmu_us_clb_arctic-wav-arctic_a0001`.

yindo referenced this issue

2026-02-15 17:15:48 -05:00

[PR #53] [MERGED] feat: add documentation on sso #184

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: open-webui/docs#53