In Review

In Progress

Completed

Main Roadmap

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 !

Command line Interface (CLI)

Grégoire Compagnon

I have too mane transcriptions. Finding right one is a challenge sometimes. Batch transcriptions may include 100+ files. This floods sidebar quickly. Adding some grouping tools to the desktop app would help:<ul><li>Project folders to collect recordings relevant to particular project</li><li>Tags to filter by company name, type of recording (like meeting, interview, important), speaker etc.</li></ul>

Project folders or tags

Roman Zhikharev

When you start a meeting recording (via meeting detection), the floating recorder stays in place. An option to hide that floating thing completely or move that to the menu bar would be really nice.

Floating meeting recorder view options

Right now, you have to type out the full speaker name. It’d be great if speaker names can be autocompleted from previously used names.

Speaker name autocomplete

Hi, I downloaded this and ran a podcast through it to find a phrase I heard earlier.<ol><li>Please make cmd-f move focus to the “search in transcript” text box</li><li>Sometimes the highlighted search results are just below the current displayed selection, so maybe there’s a scroll offset issue with the main window?</li></ol>

Center the highlighted text within the window

nickludlam

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.

iOS version

Anton

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 <a target="_blank" rel="noopener noreferrer nofollow" class="link" href="https://huggingface.co/nyrahealth/CrisperWhisper">https://huggingface.co/nyrahealth/CrisperWhisper</a> solved that issue

Improve Timestamp Accuracy

L-Ter

<ol><li>I would suggest feature, after transcribing, to get with one click translation to other language. </li><li>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.</li><li>enable link transcriptions (Facebook, Instagram, Youtube, X, Rumble) if not yet.</li><li>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).</li></ol>

Translations

Tarik Miljkovic

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., <a target="_blank" rel="noopener noreferrer nofollow" class="link" href="https://huggingface.co/nvidia/diar_sortformer_4spk-v1">https://huggingface.co/nvidia/diar_sortformer_4spk-v1</a>). It would be nice to be able to switch between models, similar to the way one can switch the models for transcribing locally.

Diarization Model Selection

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.

High Priority

LLMs integration

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.

Batch transcription

Support for bring-my-own fine-tuned Voice Models, allowing users to get enhanced transcriptions for specific use cases and domains.

Custom Voice Model Support

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.

Diarization of speakers

Proactive suggestions to record a meeting when QuickWhisper detects ongoing use of microphone by other apps (Zoom, MS Teams, Webex, etc).

Meeting Auto-Detection

Quick realtime voice recognition activated with a hotkey, enabling seamless dictation into any text field across all Mac applications for enhanced productivity and convenience.

Dictation

Mikhail

As a user I want not only to hear audio, but also see the video alongside with transcription

Support video playback

Add support of Parakeet Voice Model in addition to existing Whisper models.

Parakeet model (Experimental support)

I would like to ask for support for MacOS Shortcuts. This feature would enable me to automate my transcription workflow. I could start a transcription with a single command, exporting transcriptions to other apps, or triggering specific actions based on transcription content.

Support MacOS Shortcuts

I really need QuickWhisper to allow recording audio directly from other MacOS apps, such as Zoom, MS Teams, Webex and other communication tools. I need to capture important meetings without the need for external devices or reliance on third-party software.

QuickWhisper - lightning-fast and accurate transcriptions

Main Roadmap