Voice messages — into text, automatically

The scenario transcribes incoming voice and audio, falls back to a backup service if one fails, and returns ready text.

  • Voice turned into text
  • A backup transcriber if one fails
  • Long text split into parts
  • Reading beats listening
Set it upScriptera

How it works

Automating WhatsApp Business Cloud takes no code: a ready-made scenario does the routine for you.

  1. Starts when: Telegram Trigger1
  2. Check: Access Check
  3. If yes: Determining The Type Of Document
  4. If yes: Assigning file_id For Voice
  5. Check: Transcription Decision Node
  6. If yes: Get File GPT
  7. Then: Transcription by OpenAi
  8. Then: Assignment of variable TEXT
  9. Check: Checking the length of a message
  10. If yes: MSG - Output
  11. If no: Text Division
  12. Then: MSG - Output with chunking
  13. Then: Get File Gemini
  14. Then: Transcription by Gemini
  15. Then: Assignment of variable TEXT1
  16. Then: MSG - Starting transcription. Please wait.
  17. If no: MSG - File not recognized
  18. If no: Assigning file_id For Audio
  19. If no: MSG - No file!
  20. If no: MSG - Access denied!

You can launch this integration in Scriptera: describe the task in plain words — the scenario is built, launched and monitored for you.

Similar scenarios