From ebc390f9e74378fdaba3e79e9da4a76c436464e2 Mon Sep 17 00:00:00 2001 From: Pinapelz Date: Sat, 9 May 2026 00:27:38 -0700 Subject: implement gpt-realtime-translate --- README.md | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index c92f653..f880bf9 100644 --- a/README.md +++ b/README.md @@ -16,6 +16,14 @@ A GUI is available for configuration `server.py` serves a backend for translating incoming audio data. It expects some other client to hit the `/events` endpoint to fetch the translated data. +## Translation backends + +You can now choose between two subtitle backends in the settings dialog: + +- **Whisper + optional Ollama cleanup** +- **OpenAI Realtime translation** using `gpt-realtime-translate` (requires OpenAI API Key, billed usage) + - This bypasses `faster-whisper` and `ollama`, in this use case auto-live-tl only serves to encode PCM data into the appropriate format for `gpt-realtime-translate` + # Clients: @@ -103,7 +111,3 @@ https://github.com/user-attachments/assets/db602a11-2d13-4e58-a5e8-1d4a71c1be0e Example 2: https://github.com/user-attachments/assets/a480809e-77f7-4b66-9686-aa2ffea8333d - - - - -- cgit v1.2.3