The URL builder was prepending wss:// to the full https:// URL, producing
an invalid wss://https://... URL. Now properly converts https→wss and
http→ws before appending the /ws/transcribe path.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Audio capture started immediately after spawning the WebSocket thread,
but the WebSocket hadn't connected yet. Audio chunks sent to the
unconnected WebSocket caused a broken pipe error.
Fix: added a threading.Event that start_recording() waits on (up to
15s) before opening the audio stream. The event is set in _ws_lifecycle
after the WebSocket connects and handshake completes.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Start Transcription button now shows the error message when it fails
instead of silently reverting. Common causes:
- Missing PortAudio library on Linux
- Audio device not accessible
- Deepgram connection failure
Also added error details to backend console output and captured
the last error from the Deepgram engine for better diagnostics.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Lightweight Deepgram-only sidecar that excludes PyTorch, faster-whisper,
RealtimeSTT, and CUDA. Only includes audio capture + WebSocket streaming
to Deepgram. Requires a Deepgram API key (BYOK or managed mode).
Changes:
- client/models.py: Extracted TranscriptionResult into standalone module
so deepgram_transcription.py doesn't transitively import torch
- backend/app_controller.py: Made RealtimeTranscriptionEngine and
DeviceManager imports lazy (only loaded when remote.mode == "local")
- local-transcription-cloud.spec: PyInstaller spec excluding all ML deps
- SidecarSetup.svelte: Added "Cloud Only (Deepgram)" variant option
- build-sidecar-cloud.yml: CI workflow building cloud sidecar for all 3 OS
- sidecar-release.yml: Dispatches cloud build alongside CPU/CUDA builds
Sidecar download options are now:
- Standard (CPU): ~500 MB - local Whisper on any computer
- GPU Accelerated (CUDA): ~2 GB - local Whisper with NVIDIA GPU
- Cloud Only (Deepgram): ~50 MB - requires API key, no local models
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three changes to reduce transcription delay:
1. Send loop: queue.get() was blocking the asyncio event loop, stalling
the receive loop and delaying transcription results. Now uses
run_in_executor() to avoid blocking the event loop.
2. Block size: reduced from 4096 (~256ms) to 1024 (~64ms) for more
frequent, smaller audio chunks. Deepgram handles streaming better
with smaller packets.
3. Added punctuate=true and smart_format=true to Deepgram BYOK
params for cleaner transcription output.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New files:
- client/deepgram_transcription.py — DeepgramTranscriptionEngine with
managed mode (proxy) and BYOK mode (direct Deepgram). Sends raw binary
PCM audio over WebSocket, handles both proxy and Deepgram response formats.
Modified files:
- config/default_config.yaml — Replace remote_processing with new remote
section (mode, server_url, auth_token, byok_api_key, deepgram_model, language)
- client/config.py — Add migration from old remote_processing config
- gui/settings_dialog_qt.py — Replace Remote Processing group with
Transcription Mode section (Local/Managed/BYOK radio buttons, login/register
dialogs, balance display, model selector)
- gui/main_window_qt.py — Select engine based on remote.mode config,
add error and credits_low handlers
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
