SillyTavern/Extension-Speech-Recognition

Fork 0

mirror of https://github.com/SillyTavern/Extension-Speech-Recognition.git synced 2026-10-15 21:42:08 +00:00

[PR #22] [MERGED] Add OpenAI new transcription models #25

New issue

Closed

opened 2026-10-15 13:27:30 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-15 13:27:30 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/SillyTavern/Extension-Speech-Recognition/pull/22
Author: @Ni-co-la-s
Created: 8/17/2025
Status: ✅ Merged
Merged: 8/18/2025
Merged by: @Cohee1207

Base: main ← Head: add-gpt4o-transcription-models

📝 Commits (3)

72521a9 Add GPT-4o transcription models
e45b0b2 Add debug prefix
6128c15 Adjust formatting

📊 Changes

2 files changed (+34 additions, -15 deletions)

View changed files

📝 index.js (+11 -3)
📝 whisper-openai.js (+23 -12)

📄 Description

Description

Adds new better gpt-4o-transcribe and gpt-4o-mini-transcribe OpenAI models for STT.

Main changes

whisper_openai.js

Adds select field to select model between whisper-1, gpt-4o-transcribe and gpt-4o-mini-transcribe
Passes selected model to transcription endpoint

index.js

Change class names from Whisper (OpenAI) to OpenAI

How to Test

Open a chat/group
Go to Speech recognition extension panel
Select OpenAI as a STT provider
Press the microphone button and record a message.
Verify that the transcription is done with the proper model (from console logs or from openai api page directly)

Note

New models endpoints also support a prompt parameter, it is ignored for now

_{🔄 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/SillyTavern/Extension-Speech-Recognition/pull/22 **Author:** [@Ni-co-la-s](https://github.com/Ni-co-la-s) **Created:** 8/17/2025 **Status:** ✅ Merged **Merged:** 8/18/2025 **Merged by:** [@Cohee1207](https://github.com/Cohee1207) **Base:** `main` ← **Head:** `add-gpt4o-transcription-models` --- ### 📝 Commits (3) - [`72521a9`](https://github.com/SillyTavern/Extension-Speech-Recognition/commit/72521a93173b17c2e70ab2985e84c79f0ee20da7) Add GPT-4o transcription models - [`e45b0b2`](https://github.com/SillyTavern/Extension-Speech-Recognition/commit/e45b0b2591f54c934d86662ff336214724d1685e) Add debug prefix - [`6128c15`](https://github.com/SillyTavern/Extension-Speech-Recognition/commit/6128c1539966f68f8d6dd8d4e3a4ddf7d520655a) Adjust formatting ### 📊 Changes **2 files changed** (+34 additions, -15 deletions) <details> <summary>View changed files</summary> 📝 `index.js` (+11 -3) 📝 `whisper-openai.js` (+23 -12) </details> ### 📄 Description ## Description Adds new better gpt-4o-transcribe and gpt-4o-mini-transcribe OpenAI models for STT. ## Main changes ### whisper_openai.js - Adds select field to select model between whisper-1, gpt-4o-transcribe and gpt-4o-mini-transcribe - Passes selected model to transcription endpoint ### index.js - Change class names from Whisper (OpenAI) to OpenAI ## How to Test - Open a chat/group - Go to Speech recognition extension panel - Select OpenAI as a STT provider - Press the microphone button and record a message. - Verify that the transcription is done with the proper model (from console logs or from openai api page directly) ## Note - New models endpoints also support a prompt parameter, it is ignored for now --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-15 13:27:30 +00:00

closed this issue
added the
pull-request
label

No labels

pull-request

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

SillyTavern/Extension-Speech-Recognition#25

No description provided.

Rows
Columns