Skip to main content
Professional speech-to-text with Deepgram’s Nova models.

​
Setup

export DEEPGRAM_API_KEY=your-key

​
Usage

from praisonaiagents import AudioAgent

agent = AudioAgent(llm="deepgram/nova-2")
text = agent.transcribe("audio.mp3")
print(text)

​
Models

ModelDescription
deepgram/nova-2Latest, best accuracy
deepgram/novaPrevious generation
deepgram/whisper-largeWhisper via Deepgram

​
With Language

text = agent.transcribe("audio.mp3", language="en-US")
Deepgram excels at real-time streaming and domain-specific recognition.