Substack audio post to action items in English: send the file and get the text with the timecodes. One file may be up to 30 minutes on the free plan, no minute limit on Pro.
With the Substack audio post the engine writes the table of action items: the transcript first, then the sections Summary, Decisions, Action items. The speech is in English, the free plan gives 3 files a day, and one file is up to 30 minutes.
The transcript icon is pressed, and the transcript can be corrected or replaced by the file of the author
The widget takes the file of the Substack audio post as it is and marks the speech as English, so the engine does not have to guess what it is about.
The text of the Substack audio post is given to the instruction of the table of action items, and the answer is written in the sections Summary, Decisions, Action items, one after another.
The recording of the Substack audio post is in English, and that is one of the 99+ languages the engine reads; the setting of the widget says English and the table of action items follows.
The audio file of a post is an MP3, a WAV or an ACC file
One segment per line, the way a person wrote it down. It is the format to paste into a ticket, a chat or a document.
The start and the end time of every segment, and the speakers named separately when you ask for it.
SRT and VTT with the time of every line, so the recording can carry its own subtitles.
The transcript is edited through the API and exported as Markdown for a wiki, or as DOCX for a review.
| What | What the platform says |
|---|---|
| Where the file is | An audio post is made in the web version of the publication: Create and then Podcast. |
| What the file is | The audio file is recorded in the app or uploaded, and the transcript is opened with the transcript icon when the file has been processed. |
| What can go wrong | A video post is recorded in the browser with the Recording Studio of Substack or uploaded with Select file. |
| What the platform says | The audio file of a post is an MP3, a WAV or an ACC file. |
| What the platform says | The transcript of a post can be edited, and a transcript file of the author can be uploaded as a .txt, .srt or .vtt file. |
| Length of one file | up to 30 minutes on the free plan, no minute limit on Pro |
| Free plan | $0: 3 files a day, up to 30 minutes per file, no card |
| Pro plan | $10 a month when you pay yearly ($120 a year), or $20 a month |
A video post is recorded in the browser with the Recording Studio of Substack or uploaded with Select file. The English speech of the Substack audio post is read first, and the table of action items is what the project manager gets out of the transcript.
The instruction of the table of action items is already written.
The engine does not translate the Substack audio post from English.
Check who may download the file of the Substack audio post.
An audio post is made in the web version of the publication: Create and then Podcast. The engine reads the English speech of the Substack audio post and writes the table of action items from that text.
The recommended maximum size of a video upload is 20 GB, with a H.264 codec and an AAC audio codec. The engine does not change the file of the Substack audio post; it reads it as it is and writes the table of action items.
The engine reads the English speech and the instruction writes the table of action items in the sections Summary, Decisions, Action items; every line comes from the transcript of the Substack audio post.
One file of the Substack audio post may be up to 30 minutes on the free plan; the free plan gives 3 files a day.
Bring the file of the Substack audio post to your own disk and upload it here; the engine returns the table of action items with the time of every line.
The same task on another recording, with the same steps and the same sections.
Meeting to action itemsThe page of the task: the instruction that is written for it and an example of the answer.
Transcribe audio to textWhat the service does with a file: the formats of the export, the limits and the plans.
Reading: 4 minutesUpdated 
Transcribsi editorial team
Speakers by name, a time on every line, export to TXT, SRT, VTT, CSV and Markdown.