Developed and delivered a KoboldCPP Text-to-Speech integration for the abeiro/HerikaServer repository, focusing on backend enhancements using PHP. The work involved building a dedicated PHP module to manage TTS requests, enabling configurable endpoints and voice selection through the KoboldCPP API. To optimize performance and reduce reliance on external services, audio caching was implemented, allowing previously generated speech to be reused and minimizing API calls. This feature leveraged skills in API integration, backend development, and text-to-speech technologies, resulting in a more efficient and flexible TTS workflow within the server’s architecture. No bug fixes were recorded during this period.