Praison AI

  • Enterprise
  • Agents
  • Bot
  • Use Cases
  • University
  • Docs
Getting StartedCLIGateway & BotsAgentsCodeUIToolsMCPDeployExamplesSDKJSRustCourse

Agents

Agents
  • AI Agents
Image Agents
  • Image Generation
  • OpenAI Images
  • Azure Images
  • Vertex AI Images
  • AWS Bedrock Images
  • Recraft Images
  • Google AI Studio Images
  • Vision Agent
Video Agents
  • Video Overview
  • Migrating deprecated video model IDs
  • OpenAI Sora
  • Google Gemini
  • Azure OpenAI Sora
  • Vertex AI Veo
  • RunwayML Gen-4
  • OpenRouter Video
Audio Agents
  • Audio Overview
  • OpenAI Audio
  • ElevenLabs
  • Groq Audio
  • Deepgram
  • Google Gemini Audio
  • Azure Audio
  • Vertex AI Audio
  • MiniMax Audio
  • Fireworks AI Audio
  • AWS Polly
  • OVHcloud STT
  • Realtime Agent
Research Agents
  • Deep Research Agent
  • Research Agent
  • Web Search Agent
  • Wikipedia Agent
  • Query Rewriter Agent
Content Agents
  • Markdown Agent
  • Image Analysis Agent
  • Image to Text Agent
  • Video Agent
  • Prompt Expander Agent
Analysis Agents
  • Data Analyst Agent
  • Finance Agent
  • Planning Agent
  • Programming Agent
Utility Agents
  • Single Agent
  • Shopping Agent
  • Recommendation Agent
  • Code Agent
  • Context Engineering Agent
  • Embedding Agent
OCR Agents
  • OCR
  • Mistral OCR
Docs/Agents/Audio Agents/Groq Audio
PreviousNext

Groq Audio

Ultra-fast Whisper STT

Usage

python
from praisonaiagents import AudioAgent

agent = AudioAgent(llm="groq/whisper-large-v3")
text = agent.listen("audio.mp3")
print(text)

Models

ModelSpeed
groq/whisper-large-v3Fast
groq/whisper-large-v3-turboFaster
groq/distil-whisper-large-v3-enFastest (English)
Tip

Groq offers low-latency Whisper transcription.

PreviousNext
  • Platform
  • Use Cases
  • Agents
  • Bot
  • Enterprise
  • Partners
  • Community
  • FAQ
  • About
  • University
  • Documentation
  • GitHub

© Praison AI Limited.

Search in