Automatically transcribe voice messages sent to your Telegram bot

Voice notes sent to your Telegram bot are transcribed to text automatically and sent back as a readable message.

How the work actually flows

It branches. Exactly one path is taken.

Pattern: Exclusive Choice (4) · Simple Merge (5)

flowchart TD trig>"message received on telegram"]:::trig s0["check message type"]:::task s1["send reply message"]:::task trig --> s0 gx{"× is message text or voice"}:::gate s0 --> gx p00["download audio file"]:::task gx -->|"voice message"| p00 p01["transcribe with whisper"]:::task p00 --> p01 p10["use text as is"]:::task gx -->|"text message"| p10 jn{"○ text ready"}:::gate p01 --> jn p10 --> jn jn --> s1 out[/"readable text of voice message"/]:::out pay{{"no more replaying audio to find details"}}:::pay s1 --> out out --> pay classDef task fill:#e7f6fe,stroke:#34b8f0,color:#2c2a29 classDef svc fill:#f6f8fa,stroke:#7c8795,color:#2c2a29 classDef mi fill:#e7f6fe,stroke:#0079a8,color:#2c2a29,stroke-width:2px classDef human fill:#fff,stroke:#0079a8,color:#0079a8 classDef store fill:#f6f8fa,stroke:#0079a8,color:#2c2a29 classDef trig fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigtime fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigdata fill:#8ad4f5,stroke:#0079a8,color:#06314c,font-weight:bold classDef gate fill:#fff,stroke:#e8a23d,color:#6b4708,font-weight:bold classDef out fill:#1f9d6b,stroke:#167a53,color:#fff,font-weight:bold classDef pay fill:#06314c,stroke:#021f33,color:#fff
Starts itA stepOne path onlyPaths rejoinResultPayoff
Build size
Standard

A mid-size build with several tools working together.

Business functions
Voice & PhoneMessaging & NotificationsImage & Media Processing
Connects
TelegramOpenAI

The problem it solves

Voice messages are handy to send but painful to deal with when you are trying to skim, search, or forward what someone said. You end up replaying audio just to find one detail buried in the middle.

Who it fits

Anyone running a Telegram bot who wants voice messages handled the same as text.

How it works

  1. A message arrives in Telegram, either text or a voice note
  2. The system checks whether it is text or voice
  3. For voice notes, the audio file is downloaded automatically
  4. OpenAI's Whisper model converts the audio into text
  5. The text, whether typed or transcribed, is sent back as a message
What you get

Voice messages you can read instead of listen to

Every voice message sent to your bot arrives back as a clear written note you can read at a glance.

What you get

A text transcript of every voice message, ready to read or pass along.

What you need

A Telegram bot account and an OpenAI account.

We can build this. But should you?

The hard question is not how to build it. It is whether this is the right thing to build first.

That is what a Fractional Chief AI Officer figures out with you, before anyone writes a line of code.

Let's Talk Strategy

Related automations

Back to the AI Playbook