blurt

T

felixm 777d4bef33 Speed up transcription with a pluggable provider backend

Transcription:
- Provider-pluggable backend: each model routes to OpenAI (multipart
  upload) or OpenRouter (JSON + base64 body). Add OpenRouter's
  whisper-large-v3-turbo (Groq-served, ~216x real-time) to the tray
  menu for far lower latency than whisper-1.
- Load API keys env -> keyring -> file for both providers via a shared
  helper.
- Encode the WAV in memory and reuse a warm requests.Session (no temp file).

Other improvements:
- blurt-toggle signals the running app directly via SIGUSR1 instead of
  paying ~0.5s to import the full stack through "uv run blurt toggle".
- Remove the redundant dead blurt shell script.
- Suppress the benign Gdk-CRITICAL warning from pystray's GtkStatusIcon.
- gitignore openrouter_key.txt.

Transcription code is platform-agnostic; the Windows/Linux platform layer
is unchanged.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-05-31 08:38:05 -04:00

.gitignore

Speed up transcription with a pluggable provider backend

2026-05-31 08:38:05 -04:00

blurt-toggle

Speed up transcription with a pluggable provider backend

2026-05-31 08:38:05 -04:00

blurt.py

Speed up transcription with a pluggable provider backend

2026-05-31 08:38:05 -04:00

blurt.vbs

Initial commit

2026-05-30 23:30:37 -04:00

pyproject.toml

Initial commit

2026-05-30 23:30:37 -04:00

uv.lock

Initial commit

2026-05-30 23:30:37 -04:00