I am reaching out to know more about your pricing options for using your AI services.
We are interested in detecting emotions in live video and audio streams, and we would also like to understand if your emotion detection
models are culturally dependent and what languages are supported for accurate analysis.
Details of Our Requirements:
Video Analysis: Real-time detection of facial expressions and emotions from a live video stream.
Audio Analysis: Real-time voice analysis to identify emotions, tone, and sentiment.
Could you please provide detailed pricing information, including licensing fees, subscription options, pay-per-use rates, or any hardware requirements? Additionally, if you have any details about free trials,
demos, or consultation services, we would appreciate the information.
Furthermore, we would appreciate it if you could provide a roadmap on how to effectively use your SDK to meet our specific requirements for emotion detection in both live video and audio streams.
Thank you for your interests in DeepStream and other Nvidia products.
For the motion detection model, there is only one EmotionNet | NVIDIA NGC model provided by TAO. The model is free to download and use for commercial purposes. This model doesn’t take into account cultural dependency. The exact dataset that the model is trained on is provided in the model card. You can fine-tune with your own dataset using NVIDIA TAO. There is no pre-trained model for emotion of audio/voice.