Basic Information

appmixer.ai.groq.CreateTranscription

Create Transcription

1.0.0

Public

Generates a transcription of audio content to text.

Input Ports

in

FieldTypeDescription
Model text Insert a model ID or select one of the models available to your Groq account. Speech-to-text models are named whisper-*.
Audio File filepicker Upload an audio file (mp3, wav, etc.)
Language text Language code (ISO 639-1) to improve accuracy.
Prompt textarea Guide the model with prior text or style.
Temperature number Controls randomness of output (0 to 1).

Output Ports

out

FieldTypeDescription
Transcription -

Full Metadata