Sold by: Sonic Flow
Deployed on AWS
Smartbot is a Real-time Sentiment- Aware ML Model that delivers enhanced customer experience
Overview
Understanding Sentiment-Aware AI: The Next Step in Customer Service Evolution. While traditional AI solutions focus on transactional elements, the Smartbot ML Model is Sentiment-Aware AI, focusing on the human side of customer interactions by analyzing the sentiment and tone behind them. Sentiment-aware AI systems can detect subtle cues like vulnerability, frustration, and satisfaction. SERTS (Sentiment Evaluation in Real-time Speech) uses advanced machine learning algorithm to evaluate sentiment in real time. This helps businesses truly understand their customers voices and sentiment to deliver empathetic, AI-driven support for vulnerable customers and beyond
Highlights
- Smartbot is sentiment-aware AI that analyses the tone to detect cues like frustration or satisfaction or vulnerability. Powered by SERTS (Sentiment Evaluation in Real-time Speech). It uses advanced an ML algorithm to evaluate sentiment in Real-time as well as helping businesses understand customer sentiment and deliver empathetic AI-driven support
- SERTS deep learning algorithm performs competitively with state-of-the-art models, achieving excellent results on challenging improvised datasets. This model was trained and tested using an NVIDIA RTX 6000 Ada GPU
Details
Sold by
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.xlarge Inference (Batch) Recommended | Model inference on the ml.m5.xlarge instance type, batch mode | $10.50 |
ml.m5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.m5.xlarge instance type, real-time mode | $10.50 |
Dimensions summary
You pay by the hour for running this emotion-aware AI model, based on usage rather than a fixed subscription. Both options run on the ml.m5.xlarge instance type and are billed per host hour. The difference is the processing mode. Batch inference handles grouped data in scheduled runs, while real-time inference processes requests as they arrive for live interactions. You can choose either mode, or both, depending on how you need to run the model. Your cost scales with the number of host hours you consume.
Top-of-mind questions for buyers
The ml.m5.xlarge is a general-purpose AWS compute instance used to run the model. You are billed for the hours this instance runs, regardless of processing mode. Both options use this same instance size, so the hardware spec stays consistent across batch and real-time modes.
Charges accrue per host hour while the instance runs. A fully stopped instance does not accrue software host-hour charges. Real-time mode typically runs continuously to handle live requests, so it meters more hours. Batch mode runs only during scheduled jobs, so it meters hours only during those runs.
Both meter host hours on the same instance. Batch mode processes grouped data during scheduled runs, so you pay only for the hours those jobs take. Real-time mode processes requests as they arrive and usually stays running to stay responsive, so it accrues hours continuously. Your workload pattern determines which costs more.
www.smartbotsoftware.com
Helpful?
Vendor refund policy
Usage-based charges are generally non-refundable. If you encounter a billing error or technical issue that prevents normal use, contact us at support@smartbotsoftware.com within 30 days of the charge. We will review each request and issue a refund where appropriate. For assistance, visit smartbotsoftware.com and go to the Contact Us section.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
SmartBot V2 introduces a multimodal emotion recognition model capable of processing raw audio inputs in real time. This version supports base64-encoded .wav inputs and performs speech-to-text transcription, spectrogram generation, and text-audio fusion for emotional analysis. Compared to V1, this version has improved accuracy on diverse speakers and emotion categories
Additional details
Inputs
- Summary
SmartBot V2 accepts JSON input structured as a dictionary of base64-encoded .wav audio clips. Each entry must include a unique uid key. No text input is required—the system performs speech-to-text internally. Example format:
{ "invocations": { "uid123": "", "uid456": "" } }
- Limitations for input type
- - Audio must be mono .wav format, 16-bit PCM, 16kHz. - Max file size per audio clip: 3 MB - Each request supports up to 10 audio clips
- Input MIME type
- application/json
{
"invocations": {
"12345": "UklGRtQAAABXQVZFZm10IBAAAAABAAEA...",
"jh13d3": "UklGRkQAAABXQVZFZm10IBAAAAABAAEA..."
}
}
{
"invocations": {
"12345": "UklGRtQAAABXQVZFZm10IBAAAAABAAEA...",
"jh13d3": "UklGRkQAAABXQVZFZm10IBAAAAABAAEA..."
}
}
Resources
Vendor resources
Support
Vendor support
Smartbot provides prompt and reliable support for all users. Our team is available Monday to Friday (9 AM to 5 PM BST) to assist with technical queries. Customers can expect a response within 48 hours of raising a support request. For critical issues, we prioritise resolution with utmost urgency. We are committed to ensuring a smooth and valuable experience with Smartbot Support Email: support@smartbotsoftware.com
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Introducing Generative AI Customer and Employee experience services on Amazon BedRock. Our professional services offering is designed to enhance your business's customer and employee interactions. As AWS Conversational AI Competency partner we are focused on provding proven solutions for improving your enterprise customer and employee experiences. With Amazon Bedrock, we help enterprises access different Generative AI models to optimize customer experiences and streamline internal processes, all within your AWS environment. Achieve greater operational efficiency and customer satisfaction through our proven AI-driven services.
Help finserv contact centres evidence FCA Consumer Duty compliance by detecting customer vulnerability and distress in real time using Smartbot's sentiment-aware AI
SmartBots - Where good conversations become great customer experiences. Custom enterprise Conversational AI and Generative solutions (Chat and Voice bots) catering to bespoke use-cases
AI-powered platform with chat support, enabling users to ask data questions, create visualizations, and generate insights for informed decision-making.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.