Tokenless

Voice cloning

Serving Voice AI at $1/hr: Open-source, LoRAs, Latency, Load Balancing - Neil Dwyer, Gabber

Serving Voice AI at $1/hr: Open-source, LoRAs, Latency, Load Balancing - Neil Dwyer, Gabber

An in-depth look at Gabber's experience deploying the Orpheus text-to-speech model to production, covering latency optimization, high-fidelity LoRa-based voice cloning, and a cost-effective inference stack using vLLM and a consistent hash ring for load balancing.

Why Voice Security Is Your Next Big Problem

Why Voice Security Is Your Next Big Problem

Yishay Carmiel and Roy Zanbel of Apollo Defend explore the state of voice AI, detailing the shift from cascaded models to end-to-end speech-to-speech systems. They break down the imminent security threats, including accessible voice cloning and sophisticated agent-based attacks, and discuss the nascent defense mechanisms and the urgent need for a new layer of voice security for governments, enterprises, and consumers.