203 Commits

Author SHA1 Message Date
Beingpax
247b07a7be Added prompt detection to the retranscribe option in the history as well. 2025-09-24 11:58:32 +05:45
Prakash Joshi Pax
154748c1aa
Merge pull request #305 from nulinspiratie/fix/clipboard-context
Fix: Enable Clipboard context with custom AI enhancers
2025-09-24 07:44:41 +05:45
Serwan Asaad
1417b7a4fe minor cleanup 2025-09-22 13:53:27 +02:00
Serwan Asaad
c91f92f4d0 Fix: Enable Clipboard context with custom AI enhancers 2025-09-22 13:49:07 +02:00
Beingpax
97c6234fb3 Respect VAD flag, downloading & updated to latest version 2025-09-20 17:00:28 +05:45
Beingpax
91734bda45 Native Fluid Audio VAD 2025-09-19 19:24:02 +05:45
Beingpax
6e6773068f Simplified Parakeet transcription without Whisper VAD 2025-09-19 14:36:16 +05:45
Beingpax
afd6e91207 Centralize text formatting in main flows 2025-09-19 09:09:05 +05:45
Beingpax
b55fa981bd Fix the issue with leading trigger word not being removed in case of the trigger word available at both leading and trailing position. 2025-09-18 13:21:22 +05:45
Beingpax
2b787e8e64 Centralize hallucination filter 2025-09-16 17:30:46 +05:45
Beingpax
e6225050cc Prefer enhanced text with graceful fallback: paste enhanced falls back to original; copy last transcription now mirrors same behavior; updated Settings description to reflect single-shortcut-friendly design. 2025-09-16 10:30:58 +05:45
Beingpax
848489c98b Remove manual asset reservations 2025-09-16 10:08:19 +05:45
Alexey Haidamaka
889c3e5265 add capability to see ai request in history view 2025-09-14 00:24:10 +02:00
Alexey Haidamaka
8293bc27b7
Merge branch 'main' into feat/paste-last-enhancement 2025-09-12 21:49:17 +02:00
Alexey Haidamaka
154368e616 Added capability to paste last enhancement 2025-09-12 20:03:19 +02:00
Beingpax
0429af6678 Use whisper module in VoiceActivityDetector to resolve calling-convention conflict with whisper_vad_default_params; no functional changes 2025-09-12 14:13:31 +05:45
Beingpax
7161bc3f71 Improved the comma seperated replacement values to be consolidated 2025-09-12 11:58:26 +05:45
Beingpax
f1fb2168c2 Added support for comma-separated words for word replacement. 2025-09-12 11:21:00 +05:45
Prakash Joshi Pax
8c985c31ea
Merge pull request #290 from n0an/updateGroqModel
Update Groq Kimi K2 model name
2025-09-12 10:14:44 +05:45
Beingpax
2a4f48ac0d Optimize recorder startup by backgrounding media controls 2025-09-12 10:14:10 +05:45
Anton Novoselov
574e381b0a Update Groq Kimi K2 model name 2025-09-11 09:42:10 +01:00
Beingpax
53d1507a53 improve hallucination filter and integrate with parakeet transcription service 2025-09-06 16:56:28 +05:45
Beingpax
95e57bf3f7 Added support for retry functionality 2025-09-06 09:36:55 +05:45
Beingpax
5eacee467a Feat: Respect VAD user setting in ParakeetTranscriptionService 2025-09-06 08:57:32 +05:45
Beingpax
c0ed2dc78a Improved VAD for Parakeet model 2025-09-06 07:13:06 +05:45
Beingpax
106fd653ea feat: Integrate experimental VAD for Parakeet
This change introduces a standalone Voice Activity Detection (VAD) service and integrates it into the ParakeetTranscriptionService.

The VAD preprocesses the audio to remove silent segments, aiming to improve transcription accuracy.

This is considered experimental due to a discovered anomaly in the Swift/C bridge where timestamps were being multiplied by 100. A workaround has been implemented to correct this.
2025-09-05 18:37:16 +05:45
Beingpax
12c850f77b Open With and title cleanup 2025-09-05 11:22:14 +05:45
Alexey Haidamaka
c06d01f61e Handle retry for API rate limit errors 2025-09-04 11:10:54 +02:00
Prakash Joshi Pax
26362bb50e
Merge pull request #263 from gdmka/feature/ai-enhancement-retry-logic
Implement Retry Logic for AI Enhancement Service
2025-08-28 09:00:01 +05:45
Alexey Haidamaka
c83afac031 feat: Add retry logic to AI enhancement service 2025-08-28 03:34:12 +02:00
Brandon Weng
95061cda40 spacing 2025-08-27 14:51:36 -04:00
Brandon Weng
620b3a8d3b Remove cleanup state 2025-08-27 14:50:09 -04:00
Brandon Weng
2ea220dfed use default configs from upstream for parakeet 2025-08-27 14:48:07 -04:00
Beingpax
2aac1020f8 Added support for preserving the prompt used during enhancement on 2025-08-26 21:34:54 +05:45
Prakash Joshi Pax
6980857750
Merge pull request #258 from gdmka/gdmka-mistral-medium-latest
added mistral-medium-latest
2025-08-26 20:57:30 +05:45
Beingpax
b3257eef61 Fixed license validation and activation issue due to missing API header on 2025-08-26 20:51:29 +05:45
Alexey Haidamaka
d666343121
added mistral-medium-latest
https://docs.mistral.ai/getting-started/models/models_overview/#api-versioning

Medium offers a reasonable balance between Small and Large in output and speed. Especially now when Large is sometimes is frequently over capacity.

This is my go to model for Mistral.
2025-08-26 16:32:43 +02:00
Beingpax
68e8a21746 Clipboard context with their own tags 2025-08-26 16:55:01 +05:45
Beingpax
71fdbdfc75 Add obfuscated trial storage to prevent perpetual trial 2025-08-26 09:41:42 +05:45
Beingpax
9e29b34db1 Fix decoder state cleanup blocking transcription start with Parakeet model 2025-08-25 13:50:07 +05:45
Beingpax
6a308b81bf Update app to support Parakeet B3 model 2025-08-25 13:00:35 +05:45
Beingpax
2708cc502a Added support for Gemini models for transcription 2025-08-25 12:00:15 +05:45
Beingpax
49a3cd0f4a Add support for word replacement in non-space languages 2025-08-25 10:46:01 +05:45
Beingpax
405b7ed143 Add predefined dictionary words 2025-08-23 23:34:14 +05:45
Beingpax
edd3145bf3 Remove toggle from dictionary items 2025-08-23 23:04:08 +05:45
Beingpax
73bb3e765a Remove dictionary item dependency on local Whisper model 2025-08-23 22:15:13 +05:45
Beingpax
abe12d0dfe Fix AI assistant prompt using dictionary items as context 2025-08-23 19:32:36 +05:45
Beingpax
f13e559536 Add support for retrying the last transcription from menu bar 2025-08-23 17:16:17 +05:45
Beingpax
881957793f Log successful license validation responses 2025-08-22 10:00:39 +05:45
Beingpax
d39c660bca Logging for license validation issue 2025-08-22 02:13:09 +05:45