Does the bot listen to me live?
No. It reads a file that already exists: the voice memo you recorded. There is no microphone to open and no live session; the recording travels as a file.
Free tools
Voice to text from a phone memo
Voice to text: record a memo on the phone, send the file to the Telegram bot and get the text with a timecode on every line.
3 files a day up to 30 minutes, free99+ languagesSpeaker separation and timestamps
In short
Voice to text starts with a voice memo: record it on the phone, send the file to the Telegram bot, and the words come back in the chat with a timecode. The free plan is $0 with 3 files a day, one file up to 30 minutes.
The case
Dictation, delivered like a message
Dictation is the oldest use of speech recognition and the newest use of a chat. A phone records the memo, the file travels to the bot, and the text arrives where it can be read, corrected and exported — with no account on somebody else's platform and nothing to install on the phone.
What a voice memo turns into
| What | Value |
|---|---|
| The route | the voice memo is a file; the Telegram bot returns the text in the same chat |
| What comes back | one segment per line with the start and the end time; the speakers named on request |
| Where the file is processed | Athe recording language is detected automatically. |
| The free plan | $0: 3 files a day, up to 30 minutes per file, no card |
How to turn a voice memo into text
- 1
Record the memo on the phone
The voice memo of the phone is a file: mp4, m4a or wav. Keep it as it is; the limits of up to 30 minutes are checked on that file.
- 2
Send the file to the bot
Open the Telegram bot on this page, send the recording and wait for the answer in the same chat. Nothing has to be installed on the phone.
- 3
Correct the names, then export
Every line carries the time it starts and ends. Fix a name in the app and take the result as TXT, Markdown, SRT, VTT, CSV or DOCX.
Tips
Name the memo after the day; memos pile up.
Send the memo as it is, without converting it.
A quiet room beats a new microphone.
Questions this page answers
Can it tell two people apart?
Yes, when you ask for the split by speaker. The transcript then names the voices, which is what turns a memo into a conversation.
What happens to my recording?
Athe recording language is detected automatically. The audio is never used to train models for other customers.
How much does this cost?
The free plan is $0 with 3 files a day and up to 30 minutes per file, and no card is asked for. Pro is $10 a month when you pay yearly.
Reading: 6 minutesUpdated 
Transcribsi editorial team
Drop a recording — the text arrives in a minute
Speakers by name, a time on every line, export to TXT, SRT, VTT, CSV and Markdown.
3 files a day up to 30 minutes, free99+ languagesSpeaker separation and timestamps