M4A audio file to file in Russian: 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. The engine reads 99+ languages.
The M4A audio file becomes the minutes: the engine reads the Russian speech and the sections Attendees, Agenda, Discussion by item are written from the transcript. The free plan gives 3 files a day of up to 30 minutes.
For a voice message the Telegram Bot API asks for an .OGG file encoded with OPUS, an .MP3 file or an .M4A file
The recording of the M4A audio file is attached to the widget of the page with the language of the speech set to Russian, and the minutes comes back as a file of text.
The instruction of the task asks for the minutes and puts the answer about the M4A audio file into the sections Attendees, Agenda, Discussion by item; a claim that is not in the recording is not written.
The engine reads 99+ languages; this M4A audio file is in Russian, so the language of the widget is set to Russian for the minutes.
A voice message of the Telegram Bot API is an .OGG file encoded with OPUS, an .MP3 file or an .M4A 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 | Audacity opens an M4A file with the FFmpeg library: it allows the program to import and export a much larger range of audio formats, including M4A (AAC), AC3 and WMA. |
| What the file is | The Telegram Bot API takes an audio file only in the .MP3 or .M4A format, and it sends a voice message in the .OGG file encoded with OPUS, .MP3 or .M4A format. |
| What can go wrong | Google Drive keeps the M4A among the files it stores: any file type can be stored in Drive, and the list of the audio formats it previews names MP3, MPEG, WAV, .ogg and .opus. |
| What the platform says | In the FAQ of the FFmpeg library of Audacity the M4A is written next to the codec it carries: M4A (AAC), AC3 and WMA. |
| What the platform says | A voice message of the Telegram Bot API is an .OGG file encoded with OPUS, an .MP3 file or an .M4A 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 |
Google Drive keeps the M4A among the files it stores: any file type can be stored in Drive, and the list of the audio formats it previews names MP3, MPEG, WAV, .ogg and .opus. That is the part that depends on the M4A; everything after it is the work of the minutes, and it is the same for every recording.
The instruction of the minutes is already written.
The engine does not translate the M4A audio file from Russian.
Take the file of the M4A audio file as soon as you have it.
Bots can currently send audio files of up to 50 MB in size, and the limit may be changed in the future.
Audacity opens an M4A file with the FFmpeg library: it allows the program to import and export a much larger range of audio formats, including M4A (AAC), AC3 and WMA. The engine reads the Russian speech of the M4A audio file and writes the minutes from that text.
Bots can currently send audio files of up to 50 MB in size, and the limit may be changed in the future. The file of the M4A audio file is the input of the engine, and the minutes is written from it.
the minutes in the sections Attendees, Agenda, Discussion by item, with the time of every line of the recording of the M4A audio file.
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 minutes comes back in every one of them.
The file of the M4A audio file and the widget are enough: the engine reads the Russian speech and writes the minutes.
Reading: 4 minutesUpdated 
Transcribsi editorial team
Speakers by name, a time on every line, export to TXT, SRT, VTT, CSV and Markdown.