Recording with timecodes to a blog post 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.
What the Audacity stores is what the engine needs. The English speech becomes the blog post in the sections Headline and lead, Outline, Draft; one file may be up to 30 minutes, and 3 files a day are free.
The Time Toolbar shows the position of the record head in the hh:mm:ss format, and the format of the display is changed with its context menu
The Recording with timecodes goes to the service through the upload widget; the speech is English, and the blog post comes back into the chat.
The instruction of the blog post is written for this task already: it reads the text of the Recording with timecodes and asks for Headline and lead, Outline, Draft, and it keeps every claim to the transcript.
The speech of the Recording with timecodes is English, one of the 99+ languages the engine reads, and the widget is left on English while the blog post is written.
Right after the recording it is strongly recommended to export it at once to WAV or AIFF as a safety copy, before the editing starts
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 | A Label Track is an additional track of the project: the labels in it mark points or regions of the audio tracks, and the label track itself holds no audio. |
| What the file is | The Time Toolbar is read-only and shows the current position of the play head or of the record head, and while the recording runs it follows the record head. |
| What can go wrong | The recording of Audacity is taken from the sound input of the computer or from a mixer, and the source is chosen in the Audio Setup Toolbar or in the Audio Settings Preferences. |
| What the platform says | Audacity labels a point, a single moment of the audio, or a region, a span with a start and an end time; a point label is a region label with the same start and the same end. |
| What the platform says | The labels are imported and exported as text label files, and the text of a label can be kept for annotation or for transcription. |
| 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 |
The Recording with timecodes from the Audacity holds the voices and the order of the words. The Time Toolbar is read-only and shows the current position of the play head or of the record head, and while the recording runs it follows the record head. From that text comes the blog post, in the sections Headline and lead, Outline, Draft.
The sections of the blog post are the same for every recording.
The engine does not translate the Recording with timecodes from English.
Take the file of the Recording with timecodes as soon as you have it.
A very large number of labels in one project, hundreds or thousands, can make Audacity noticeably sluggish.
The Time Toolbar is read-only, so the audio position cannot be reset with it: the Selection Toolbar is needed for that.
A Label Track is an additional track of the project: the labels in it mark points or regions of the audio tracks, and the label track itself holds no audio. The engine reads the English speech of the Recording with timecodes and writes the blog post from that text.
A very large number of labels in one project, hundreds or thousands, can make Audacity noticeably sluggish. The file of the Recording with timecodes is the input of the engine, and the blog post is written from it.
the author of the post. The transcript of the Recording with timecodes is read first, and the blog post comes out of it in the sections Headline and lead, Outline, Draft.
3 files a day of up to 30 minutes every day, and the export of the text in the formats of the service, so the blog post comes back in every one of them.
The file of the Recording with timecodes and the widget are enough: the engine reads the English speech and writes the blog post.
The same task on another recording, with the same steps and the same sections.
Video to a blog postThe 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.