> Markdown version of [/events/world-congress-2026-europe/sessions/1467-smaller-voice-models](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1467-smaller-voice-models). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Smaller Voice Models


- **Date:** Thursday, Jul 9, 2026
- **Time:** 13:25–13:30 (5 min)
- **Room:** Airstream 1
- **Event:** World Congress 2026 Europe

## Recording

[Watch recording](https://www.wearedevelopers.com/videos/100066-smaller-voice-models)

## Description

In this talk, we’ll cover why some tasks only need smaller models: benefiting from zero cost, privacy, low latency, and offline reliability. Using voice AI as the example, we’ll explore how compact text-to-speech models can run on-device or on-premise, avoiding the cost and latency of cloud-only systems. We’ll share practical lessons from building smaller voice models, where they work well, where larger models are still useful, and how developers can think about model size as a product decision rather than just a benchmark. The session is aimed at anyone building real-time AI applications, voice agents, embedded tools, or privacy-sensitive user experiences.

## Speaker

### [Sohaib Ahmad](https://www.wearedevelopers.com/@sohaib-ahmad)

CEO of Neuphonic


## Related talks at this congress

- [Future of Mobile AI. What On-Device Intelligence Means for App Developers](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1298-future-of-mobile-ai) — Sasha Denisov
- [Fine-Tuning Small Language Models for Agentic AI](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1389-fine-tuning-small) — Björn Buchhold
- [Compress, Cut, and Distill: The Latest Gen AI Model Compression Techniques in Practice](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1286-compress-cut-and) — Sergio Perez
- [Owning the Inference Layer: When and How to Run your Own Models](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/983-owning-the-inference) — Taylor Jordan Smith