Deepgram's VP of Research Andrew Seagraves joins to explore the science and engineering behind modern speech recognition systems. Hermes and Andrew dive deep into why speech recognition isn't a solved problem, the two-stage training process of speech-to-text models, and the challenges of balancing real-time latency with accuracy. The conversation covers Deepgram's origins from dark matter research, power laws in speech data, buffer-based architectures for real-time transcription, and frontier challenges like multilingual code-switching, emotion detection, and conversational dynamics. Andrew shares insights on model deployment, customer use cases from NASA to food ordering, and the future of self-adapting speech models.

Google's Ninny Wan, Product Lead for AI Content Safety, joins to discuss the evolution of AI content moderation in the age of GenAI. The conversation covers Google's approach to semantic understanding, multilingual moderation across 140+ languages, synthetic data generation for training, and the balance between user freedom and safety. Ninny shares insights on transformer models, human-in-the-loop processes, cross-functional safety reviews, and Google's on-device privacy-compliant features like sensitive content warnings.

Trulience's Head of Growth Richard Bowdler joins to discuss the world of interactive digital avatars and conversational AI. Hermes and Richard explore how Trulience creates lifelike avatars, the technology behind real-time client-side rendering, multilingual support, and real-world applications from healthcare to customer service. The conversation covers the evolution from capture cages to modern avatar creation, competitive advantages in scalability, and the democratization of AI expertise through visual interfaces.

In this episode, Palabra's Artem Kukharenko (Co-Founder) and Ivan Kuzin (Head of Business Development) join to discuss the Palabra real-time speech-to-speech translation technology, the inspiration behind Palabra, common misconceptions about AI translation, the balance between latency and accuracy, and the challenges of voice cloning and intonation. The conversation also covers the applications of their technology, user feedback, differentiation in a competitive market, privacy and data security, benchmarking, developer experience, and future advancements in AI and speech translation.

Agora's Ben Weekes joins to discuss the world of voice-first conversational AI. Hermes and Ben delve into the differences between voice and chat-based systems, explore the real-world applications of conversational AI, and break down the technology stack involved in creating effective voice agents. The conversation also touches on virtual avatars, infrastructure challenges, and the various conversational AI frameworks available for developers.