OVHcloud STT

OVHcloud AI speech-to-text

Setup

export OVH_AI_ENDPOINTS_ACCESS_TOKEN=your-token

Usage

from praisonaiagents import AudioAgent

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

Models

Model	Description
ovhcloud/whisper-large-v3	Whisper Large v3
ovhcloud/whisper-medium	Whisper Medium