From voice cloning and noise suppression to emotion detection and speech synthesis, Audio AI is reshaping how machines hear—and how people are heard.
These instructor-led courses dive into the technologies powering intelligent sound: audio signal processing, deep learning architectures, and real-time voice interaction systems.
Participants can join online live training via interactive remote desktop, or opt for onsite sessions in Sofia, where each hands-on lab tackles real-world challenges like echo removal, voice detection, or audio synthesis.
From in-house R&D labs to product innovation teams, organizations in Sofia can host onsite training at their own location or collaborate face-to-face at a NobleProg training center built for sonic experimentation.
Also known as Voice AI, Intelligent Audio, or Speech AI, this training is ideal for developers, product teams, and researchers pushing the boundaries of machine listening.
NobleProg – Your Local Training Provider
Crystal Business Center
ул. "Осогово" 40, Sofia, Bulgaria, 1303
Crystal Business Center is located in the central part of Sofia, on the corner of "Osogovo" street. and "Todor Aleksandrov" blvd. The building is easily accessible by metro (only 50 m from Opalchenska station) and other public transport. Its total area is 8000 sq.m. The office area is 6171 sq.m.
Voice assistant platforms like Amazon Alexa, Google Dialogflow, and Rasa offer powerful frameworks for developing intelligent, voice-driven applications for both public and internal use cases.
This instructor-led, live training (online or onsite) is aimed at intermediate-level developers and design teams who wish to build, train, and deploy conversational voice interfaces that automate workflows and support users naturally via speech.
By the end of this training, participants will be able to:
Design conversational flows and interaction models for voice UIs.
Develop voice assistants using tools like Dialogflow, Alexa, and open-source frameworks such as Rasa.
Integrate assistants with back-end APIs, databases, and third-party services.
Deploy assistants to smart devices or web-based voice apps.
Format of the Course
Interactive lecture and discussion.
Lots of exercises and practice.
Hands-on implementation in a live-lab environment.
Course Customization Options
To request a customized training for this course, please contact us to arrange.
Voice cloning and speech generation with AI allows users to replicate human voices or generate synthetic speech using deep learning models and speech synthesis techniques.
This instructor-led, live training (online or onsite) is aimed at intermediate-level professionals who wish to create, evaluate, and apply voice cloning and TTS systems in real-world projects.
By the end of this training, participants will be able to:
Understand the core concepts behind neural speech synthesis and voice cloning.
Evaluate commercial and open-source TTS platforms.
Clone voices from sample recordings using ethical and legal guidelines.
Integrate synthetic voices into applications, IVRs, or media pipelines.
Format of the Course
Interactive lecture and discussion.
Lots of exercises and practice.
Hands-on implementation in a live-lab environment.
Course Customization Options
To request a customized training for this course, please contact us to arrange.
Speech recognition and transcription using AI involves converting spoken language into written text through machine learning models and natural language processing systems.
This instructor-led, live training (online or onsite) is aimed at intermediate-level professionals who wish to implement, evaluate, and optimize AI-powered speech-to-text solutions for real-world use cases.
By the end of this training, participants will be able to:
Understand how modern speech recognition models are trained and deployed.
Evaluate open-source and commercial APIs for speech-to-text transcription.
Handle multilingual and domain-specific transcription challenges.
Build simple transcription workflows for different audio sources.
Format of the Course
Interactive lecture and discussion.
Lots of exercises and practice.
Hands-on implementation in a live-lab environment.
Course Customization Options
To request a customized training for this course, please contact us to arrange.
Audio AI refers to artificial intelligence technologies that interpret, analyze, generate, or interact with audio signals, including human speech, environmental sounds, and music.
This instructor-led, live training (online or onsite) is aimed at beginner-level professionals who wish to understand how AI is applied in the audio domain for business, communication, automation, and innovation purposes.
By the end of this training, participants will be able to:
Understand what Audio AI is and how it is used in real-world settings.
Identify different categories of audio AI tools (e.g., transcription, classification, generation).
Explore business cases in customer service, security, compliance, and media.
Evaluate AI tools and services suitable for enterprise audio applications.
Format of the Course
Interactive lecture and discussion.
Lots of exercises and practice.
Hands-on implementation in a live-lab environment.
Course Customization Options
To request a customized training for this course, please contact us to arrange.
Online Audio AI training in Sofia, Speech AI training courses in Sofia, Weekend Speech AI courses in Sofia, Evening Intelligent Audio training in Sofia, Audio AI instructor-led in Sofia, Voice AI coaching in Sofia, Audio AI instructor in Sofia, Audio AI on-site in Sofia, Speech AI one on one training in Sofia, Online Speech AI training in Sofia, Intelligent Audio trainer in Sofia, Speech AI private courses in Sofia, Speech AI boot camp in Sofia, Evening Speech AI courses in Sofia, Intelligent Audio instructor-led in Sofia, Weekend Speech AI training in Sofia, Speech AI classes in Sofia
