Seznam needed to automate night radio broadcasting to free up human resources for creating quality content instead of reworking material for radio.
Automation and personalization of night radio broadcasting with AI
Client NameSeznam
Client CountryCzech Republic
- Client typeEnterprise
- IndustryMarketing & Media
- Application areasContent, Media & Communications, Data & Analytics / Business Intelligence, Marketing, Sales & Customer Engagement
- AI technologiesConversational AI (chatbots, voicebots), Large Language Models (LLMs), Natural Language Processing (NLP)
- Business impactsCustomer Experience & Market Growth, Operational Efficiency & Cost Savings
- Data typesAudio Data, Textual Data
- Delivery modelsProduct / Licensed Software, Service / Subscription
- DeploymentsCloud
- Key capabilitiesConversational & Language Interaction, Generative Content & Synthetic Data
- Project stagesInitial Production Deployment
- Solution formsAPI / Micro-service Interface, Automated Backend Process
Solution Description
Problem description
Solution
We developed a system of AI agents that automate the entire broadcasting process. Each agent focuses on a specific task such as playlist creation, news organization, and script writing, all working together for seamless broadcasting.
Main Users of the Solution
Radio operators, content creators
Project timeframe (months)
4-6
Technologies used
Large language models, NLP, text-to-speech models
Additional services
- Annotation / synthetic data / dataset extension
- AI model selection and customisation
- Providing MLOps infrastructure
Implementation
Project Owner on the Client's Side
Head of Innovation / Digital Transformation
Participation on the Client's Side
- Domain / process experts
- Project and change management
- End users
Form of Supplier Involvement
Joint implementation with the client
Operation and Maintenance
Operational Model
Client’s internal team
Needed Competencies on the Client's Side
Data specialists, radio operators
Other Resources or Infrastructure
Cloud infrastructure, vendor support.
Impact and Results
Qualitative Benefits
Automation of night broadcast routines; improved content quality; reduced need for night shifts.
Quantitative Results
Operational costs reduced by up to 60%; possibility to run with a single operator; increased potential for personalization.
Client Feedback
“Broadcast automation has enabled Seznam to advance in innovation and efficiency both operationally and in content quality.”
Lessons Learned and Recommendations
Key Success Factors
Effective task distribution among AI agents, collaboration with the client’s team.
Biggest Challenges
Ensuring sufficient quality of automated scripts, integration into existing processes.
Recommendation for Others
Implement AI to automate repetitive tasks and maximize employee performance on creative projects.
Promotion
- CompanyBlindspot Solutions
- ContactMichaela Peterková
- Emailmichaela.peterkova@adastragrp.com
- Websitehttps://blindspot.ai
- AddressKarolinská 706/3, 186 00 Praha