[PR #430] [MERGED] Speech To Text (STT) Documentation #526

New issue

Closed

opened 2026-10-18 14:12:44 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-18 14:12:44 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/open-webui/docs/pull/430
Author: @danielrosehill
Created: 3/2/2025
Status: ✅ Merged
Merged: 3/3/2025
Merged by: @tjbck

Base: main ← Head: STT

📝 Commits (4)

ff1f2d0 Add backup tutorial and maintenance category
5fac1e1 Added new cat for STT
fd46e59 STT documentation
bbffdcc Fix image paths and remove .gitignore from PR

📊 Changes

12 files changed (+406 additions, -0 deletions)

View changed files

➕ docs/tutorials/maintenance/_category_.json (+7 -0)
➕ docs/tutorials/maintenance/backups.md (+305 -0)
➕ docs/tutorials/speech-to-text/_category_.json (+7 -0)
➕ docs/tutorials/speech-to-text/env-variables.md (+25 -0)
➕ docs/tutorials/speech-to-text/stt-config.md (+62 -0)
➕ static/images/tutorials/stt/endstt.png (+0 -0)
➕ static/images/tutorials/stt/image.png (+0 -0)
➕ static/images/tutorials/stt/stt-config.png (+0 -0)
➕ static/images/tutorials/stt/stt-in-progress.png (+0 -0)
➕ static/images/tutorials/stt/stt-operation.png (+0 -0)
➕ static/images/tutorials/stt/stt-providers.png (+0 -0)
➕ static/images/tutorials/stt/user-settings.png (+0 -0)

📄 Description

Documentation for STT including environment variables (with link to main .env page) and a list of providers covering the recent addition of Deepgram.

I'm not sure if you will like the environment variable idea, my thinking and logic was that the current list is extremely long and challenging to navigate, so I thought that excerpting just a few values would be useful. There may be a more intelligent way to do this in Docusaurus, if so, please modify.

I've also noted that there are a couple of user level STT settings that are not in the admin settings page. The documentation which I authored reflected my understanding of the difference between these, namely that the user settings serve as overrides for the admin settings.

Finally .. I may be mistaken about the fact that a .env variable for the Deepgram API key hasn't been added yet and so must be configed via the UI.

Maybe Worth Adding

I thought it best to keep this documentation tight and not provide extraneous details but for those who are interested in STT it may be worth providing a reference of supported models for DeepGram and any others that come in the future. Pricing could be added too, although that would mean that the documentation would become almost instantly updated.

Shortcut Keys

I'm not aware of any keyboard shortcuts specifically to support STT. If they just haven't been documented yet ... please add!

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/docs/pull/430 **Author:** [@danielrosehill](https://github.com/danielrosehill) **Created:** 3/2/2025 **Status:** ✅ Merged **Merged:** 3/3/2025 **Merged by:** [@tjbck](https://github.com/tjbck) **Base:** `main` ← **Head:** `STT` --- ### 📝 Commits (4) - [`ff1f2d0`](https://github.com/open-webui/docs/commit/ff1f2d07bf84bd265e96585dbe8bcd45d73f0105) Add backup tutorial and maintenance category - [`5fac1e1`](https://github.com/open-webui/docs/commit/5fac1e1af3eeb40d3eb6b7471039450745d77862) Added new cat for STT - [`fd46e59`](https://github.com/open-webui/docs/commit/fd46e595aab7de4d802e1a53494259ff45e1c9ac) STT documentation - [`bbffdcc`](https://github.com/open-webui/docs/commit/bbffdcceb9e576983d80f9f14f7ad10d36c0b457) Fix image paths and remove .gitignore from PR ### 📊 Changes **12 files changed** (+406 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `docs/tutorials/maintenance/_category_.json` (+7 -0) ➕ `docs/tutorials/maintenance/backups.md` (+305 -0) ➕ `docs/tutorials/speech-to-text/_category_.json` (+7 -0) ➕ `docs/tutorials/speech-to-text/env-variables.md` (+25 -0) ➕ `docs/tutorials/speech-to-text/stt-config.md` (+62 -0) ➕ `static/images/tutorials/stt/endstt.png` (+0 -0) ➕ `static/images/tutorials/stt/image.png` (+0 -0) ➕ `static/images/tutorials/stt/stt-config.png` (+0 -0) ➕ `static/images/tutorials/stt/stt-in-progress.png` (+0 -0) ➕ `static/images/tutorials/stt/stt-operation.png` (+0 -0) ➕ `static/images/tutorials/stt/stt-providers.png` (+0 -0) ➕ `static/images/tutorials/stt/user-settings.png` (+0 -0) </details> ### 📄 Description Documentation for STT including environment variables (with link to main .env page) and a list of providers covering the recent addition of Deepgram. I'm not sure if you will like the environment variable idea, my thinking and logic was that the current list is extremely long and challenging to navigate, so I thought that excerpting just a few values would be useful. There may be a more intelligent way to do this in Docusaurus, if so, please modify. I've also noted that there are a couple of user level STT settings that are not in the admin settings page. The documentation which I authored reflected my understanding of the difference between these, namely that the user settings serve as overrides for the admin settings. Finally .. I may be mistaken about the fact that a `.env` variable for the Deepgram API key hasn't been added yet and so must be configed via the UI. ## Maybe Worth Adding I thought it best to keep this documentation tight and not provide extraneous details but for those who are interested in STT it may be worth providing a reference of supported models for DeepGram and any others that come in the future. Pricing could be added too, although that would mean that the documentation would become almost instantly updated. ## Shortcut Keys I'm not aware of any keyboard shortcuts specifically to support STT. If they just haven't been documented yet ... please add! --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-18 14:12:44 +00:00