Deepgram

Real-time transcription with Deepgram

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

Model	Description
deepgram/nova-2	Latest, best accuracy
deepgram/nova	Previous generation
deepgram/whisper-large	Whisper via Deepgram

With Language

text = agent.transcribe("audio.mp3", language="en-US")

Deepgram excels at real-time streaming and domain-specific recognition.