Transcribe Telegram voice notes into text automatically

Turns any voice message sent in Telegram into a clean text transcript, sent right back to the sender.

How the work actually flows

A straight line. Runs once per each message chunk of the transcript.

Pattern: Sequence (1) ยท Multiple Instances with a priori Design-Time Knowledge (13)

flowchart TD trig>"voice message received"]:::trig s0["save voice audio file"]:::task s1["transcribe audio to text"]:::svc s2["split into message chunks"]:::task s3[["send transcript to sender"]]:::mi trig --> s0 s0 --> s1 s1 --> s2 s2 -->|"one per each message chunk of the transcript"| s3 out[/"text transcript delivered"/]:::out pay{{"written record without listening to audio"}}:::pay s3 --> 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 stepAn outside serviceRuns once per itemResultPayoff
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

You receive voice notes but don't have time to listen to them, or you need a written record for reference. Manually transcribing audio messages is slow and easy to put off.

Who it fits

Anyone who receives voice messages on Telegram and wants a written version, like busy managers or support teams.

How it works

  1. A voice note is sent to a Telegram bot
  2. The audio file is saved and processed
  3. The audio is transcribed into text using OpenAI Whisper
  4. Long transcripts are split to fit Telegram's message limits
  5. The text is sent back to the sender
What you get

Voice notes turned into text you can skim

Any voice message sent on Telegram comes back to you as a clean written transcript in moments.

What you get

A text transcript of the voice message, delivered back through Telegram.

What you need

A Telegram bot and an OpenAI API key.

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