In Review
4Under consideration
Allow returning to main UI during transcription/speaker detection
Right now, when transcription or speaker detection is running, you can’t go back to the main UI. If you leave the view, transcription/speaker detection is canceled. It’d be great to be able to navigate back to the list, view other transcripts, etc. since transcription/speaker detection can take very long.
Translations
I would suggest feature, after transcribing, to get with one click translation to other language. even to have 2 column layout side by side to see original and translation texts. I like that Turboscribe has similar thing, so we can learn foreign languages that way, by transcribing online videos. enable link transcriptions (Facebook, Instagram, Youtube, X, Rumble) if not yet. maybe even allow export to some google sheets and some flashcard software (desktop ones), to have table with original words and verbs, and translations. So that we can print it, and learn language (without repeating words on ourself, nothing stays in head).
Word-Level Timestamp Option
It would be awesome to have word-level accuracy for the timestamps. For some in research, this is very important, to improve annotation accuracy.
Center the highlighted text within the window
Hi, I downloaded this and ran a podcast through it to find a phrase I heard earlier. Please make cmd-f move focus to the “search in transcript” text box Sometimes the highlighted search results are just below the current displayed selection, so maybe there’s a scroll offset issue with the main window?
In Progress
2Actively being built
Diarization Model Selection
I would love to see other ways of automatically diarizing the transcripts. The current implementation works if the audio is great, however there are other approaches existing already (e.g., https://huggingface.co/nvidia/diar_sortformer_4spk-v1). It would be nice to be able to switch between models, similar to the way one can switch the models for transcribing locally.
Trigger transcription of existing recordings by ID
Hi, I'm using MeetMic with the local API and an Obsidian integration. I often have back-to-back meetings, so I've disabled automatic transcription to avoid interfering with recording. I'd like to automate transcription of existing untranscribed meetings at the end of each day, processing them sequentially. I can identify untranscribed meetings using GET /api/v1/transcriptions/:id and isTranscribed: false, but I couldn't find an API or CLI command to start transcription for an existing recording by ID. Is there a supported way to trigger the native Transcribe action programmatically, without reimporting the audio or creating duplicate entries? Thanks!
Completed
75Recently shipped
LLMs integration
I need QuickWhisper to seamlessly integrate with leading LLM platforms, ensuring access to up-to-date language processing capabilities: summarization, sentiment detection, key points extractions, etc.
iOS version
As a user of iOS, I want to record in-person meetings and voice memos on my mobile device, so that I can transcribe and save them without using my Mac.
Improve Timestamp Accuracy
The timestamps, especially using diarization, do sometimes drift a significant amount (i.e., often more than 2-3 seconds). I am running on a M1 mac. Maybe you could take a look at how https://huggingface.co/nyrahealth/CrisperWhisper solved that issue
Batch transcription
I'd like to ask to allow users to upload and transcribe multiple audio or video files simultaneously, significantly streamlining the transcription process. By enabling batch transcription, I can handle larger volumes of content in less time than transcribing one file at a time.
Custom Voice Model Support
Support for bring-my-own fine-tuned Voice Models, allowing users to get enhanced transcriptions for specific use cases and domains.
Diarization of speakers
I want to suggest including diarization of speakers in QuickWhisper. This feature would automatically distinguish and label different speakers within a recording, clearly identifying who is speaking at any given time. This will make transcriptions more readable and easier to analyse, particularly for multi-speaker environments such as interviews, meetings, and panel discussions.
Meeting Auto-Detection
Proactive suggestions to record a meeting when QuickWhisper detects ongoing use of microphone by other apps (Zoom, MS Teams, Webex, etc).
Dictation
Quick realtime voice recognition activated with a hotkey, enabling seamless dictation into any text field across all Mac applications for enhanced productivity and convenience.
Support video playback
As a user I want not only to hear audio, but also see the video alongside with transcription
Command line Interface (CLI)
It would be nice to be able to call QuickWhisper from CLI. Even better, having the ability to give arguments like model, language… And direct export parameters !