All projects
Personal project
VoiceMax
An async audio pipeline that stays responsive on long recordings.
Speech to text, emotion classification and LLM based summarisation over a single asynchronous Python pipeline. Batching and background processing keep response latency flat as recordings get longer, instead of making the user wait for the whole file.
- Role
- Personal project.
- Period
- 2025
- Status
- Built
- Built with
- Python · asyncio · Speech to text · LLM summarisation
- Async
- batching and background work
- 3 stages
- transcribe, classify, summarise