AIU. - Artificial Intelligence Utility

<< Click to Display Table of Contents >>

Navigation:  3. Script Language > AI - Artificial Intelligence Commands > AIU. - OpenAI API > !Core Operations >

AIU. - Artificial Intelligence Utility

AIU.SpeechToText

Previous Top Next


MiniRobotLanguage (MRL)

 

AIU.SpeechToText
Transcribes an audio file to text using the Whisper API.

 

Intention

 

The AIU.SpeechToText command (aliased as AIU.Stt) converts spoken audio from a file into written text. It sends the audio data to the OpenAI Whisper API, which processes it and returns an accurate transcription. This is incredibly useful for automating tasks that involve processing voice notes, meeting recordings, or any other audio input.

 

It’s your robot’s ear—AIU.SpeechToText listens to an audio file and tells you exactly what was said.

 

Illustration

 

┌──────────────────────────────┐

│ Audio File (audio.mp3)       │

├──────────────────────────────┤

│   "Hello, world."            │

├────────────┬─────────────────┤

│ AI Whisper │ Result          │

├────────────┼─────────────────┤

│ Processes… │ "Hello, world." │

└────────────┴─────────────────┘

Converting an audio file into text.

 

Syntax

 

AIU.SpeechToText|$$PTH|$$RET

 

Parameter Explanation

 

P1 - $$PTH - (Variable, String, Required)

The full path to the audio file to be transcribed (e.g., "C:\audio\meeting.mp3").

 

P2 - $$RET - (Variable, String, Required)

The variable where the transcribed text will be stored. On failure, this variable will be empty.

 

Examples

 

'***********************************

' AIU.SpeechToText - Sample 1: Basic Transcription

'***********************************

VAR.$$KEY=sk-YourSecretKeyHere

AIU.SetKey|$$KEY

 

VAR.$$PTH=?path\audio_sample.mp3

AIU.SpeechToText|$$PTH|$$TXT

 

' Check for errors from the API call

AIU.GetLastError|$$ERR

JNZ.$$ERR|Lab_failed

 

MBX.Transcription Result:|$$TXT

END.

 

 

Remarks

 

- The alias AIU.Stt can be used for convenience.

- The transcription model can be changed using the AIU.SetSttModel command. The default is "whisper-1".

- Supported audio file formats include mp3, mp4, mpeg, mpga, m4a, wav, and webm.

- On failure, an error is set which can be retrieved with AIU.GetLastError and AIU.GetLastErrorMsg.

 

See also:

 

AIU.TextToSpeech

AIU.SetSttModel

HTP.UploadFile