Main Roadmap

Name the transcript automatically based on its content

Most of the transcripts from my links are labeled as "Generic," so I have to rename them myself, which takes time. It would be much better if they could be named automatically based on their content.

Clickable timestamps

Timestamps in Transcript and Summary section should be clickable so we can listen that particular section rightaway.

Allow Chat and custom prompts for a Group of recordings

Feature to set a chat and prompt over a set of recording on the same topic (example - summarize the common points from these 5 videos about xx topic, consolidate the events in chronological sequence from these 4 recordings, create a blog from these 2 videos highlighting pro and cons etc)

Cyrillic text

Some countries use Cyrillic alphabet, there should be option to choose if you want Latin or Cyrillic for some countries.

Exact Verbatim transcription

Can we get an option to keep or remove all the " Um, Aw, Uh, " in the transcription?

Please fix Mongolian language issue

The app is experiencing issues when using the Mongolian language, as it appears to select a different language and provide a jumbled transcript.

Please fix Georgian STT

Hi, there are a few STT platforms that have Georgian in the language list. So, I was happy to see that you do have support for my language. Unfortunately, your STT does not work properly for Georgian. Please see example here https://transcript.lol/read/youtube/@khanacademykartuli/6601453ad2f24aea73b1f72b?view=transcript The first issue is the script. It wrote most of the transcript in Latin, like transliteration. Where it did use Georgian, it's just a jumble of letters (not like proper words without spaces). But, looking through the Latin text it looks like it did an ok job. Here, on this screenshot you can see the main issues. These are that it breaks apart words where there is no need for it ( the + signs) and combines some words (the - sign). Also, misses some sounds (the added letters), or mishears (the crossed over letters with additions). Could you please fix these? If you need some help in crowd-sourcing/ labeling the correct & incorrect output to train the AI, I can share it with my community and we will contribute free of charge. If you gift some Credits to the contributors more will join, but there will be a few, including me, that would contributors for free. Our community volunteers for development of Georgian AI by crowd-sourcing data. Our goal now is to help develop Georgian STTs. We contribute to the Common Voice open source dataset. Added 200+ hours the dataset and continue growing it. https://commonvoice.mozilla.org/en/datasets

Auto detect speaker names from content

The speaker identification in the summaries is pretty good and it would be useful to have this automatically applied to the main transcript.

More Precise Timestamps?

Is it possible to add the ability to adjust how many timestamps are provided in the transcription? Instead of a paragraph being 0:00 - 0:55, can we adjust and make every line a timestamp so each sentence or even phrase it’s it’s on timestamp? This would be extremely helpful since I ask AI a lot of questions and it typically misses exact timestamps due to the timestamps being rough estimates or simply way off because the timestamps are too broad. This would be extremely helpful, thank you for all that you have done already.

Recording tagging

Please add tagging feature for better search experience. Thank you.

Spotify audio podcast transcriptions

Audio Enhancement / Noise Reduction for Audio Files

I want a feature that can clean up audio files to make the speaking more crisp and clear (e.g., noise reduction, audio enhancement) before or during transcription. This would help improve transcription accuracy for files with background noise.

Email-to-Transcribe Service for Voicemail WAV Files

I want to be able to forward an email containing an audio file (like a voicemail WAV file from my phone system) to a specific Transcript LOL email address to get it transcribed. I would also like the final transcription to be emailed back to me so I can read it instead of playing the recording. This would automate my voicemail transcription process.

Multi-language transcription in a single file

Users need the ability to transcribe audio files containing multiple languages, particularly for scenarios like immigration hearings in the United States where an interpreter is present. The system should be able to identify and transcribe different languages within the same audio file, attributing the correct language to each segment.

Mobile/Android App

So we can share audio/video to transcribe directly to the app. Use case: I often gather my thoughts on my recording app and then transcribe them. For now, this is lots of work, as I have to upload each file. A great feature would be to be able to directly record in the app and then have it transcribed and automatically summarized

Organize Transcripts

Ability to rename transcript Ability to put transcript in to projects/folders

Export to DOC file

It would be great if we could get an export of a transcript in Doc format.

Custom Prompts

Custom prompts to create the exact content assets you need. You can customize the outputs of your content so your content will be unique to your specific needs.

Automate Tasks

i have a podcast and like to automate the transcription. Any trigger for automation would be very helpfull like webhook or rss-feed. And sending the blogpost automaticly to the blog would be a next good step. Or please build an integration to zapier, make.

An option to choose between Claude and Open AI for content

It'd be nice to have the control to choose the preferred model to generate content based on the transcript.

Batch upload of mp3 instead of 1 by 1

A feature to upload multiple MP3 or audio files and download individual transcriptions for each file when completed, as well as the option to download transcriptions either individually or in batches.

Copy button to copy whole transcript at once

Misspelling of names

Need to be able to edit all generated output to fix misspelling of names.

A Chrome extension to send URLs to transcription queue