I build voice AI systems that hold up in production. Speech models, real-time infrastructure, and the orchestration layer in between.
Founder of Mahimai AI Solutions — production voice AI on the open stack: LiveKit and Pipecat.
What I work on
- Fine tuning and evaluating TTS and STT models
- Real-time voice infrastructure: LiveKit, Pipecat, WebRTC, SIP
- Linguistic frontend, turn-taking, and interruption handling
- Concurrency, latency, and cost at production scale
Contributor to livekit-agents · FastRTC
Author of Voice Agents Handbook
| Package | What it does | Downloads |
|---|---|---|
| voicegateway | Observability and inference routing for voice AI |  |
| openrtc | Shared memory layer for multi-agent LiveKit workers |  |
| envoic | Horizontal voice AI infrastructure toolkit |  |
| fastrtc-whisper-cpp | whisper.cpp STT backend for FastRTC |  |
| fastrtc-canary | NVIDIA Canary STT backend for FastRTC |  |
| vapiserve | Custom tool server for Vapi |  |
| locallens | Local inference tooling |  |
Python, with Go where it matters.
Available for voice AI consulting. Book a call
- Merged PR 324 - gradio-app/fastrtc
- Merged PR 125 - gradio-app/fastrtc
- Merged PR 1 - mahimairaja/skills-introduction-to-github
- Merged PR 2325 - jupyter-naas/awesome-notebooks
- Merged PR 27 - richarddushime/Implementing-Facial-Recognition-and-Biometric-Attendance-Monitoring-in-Educational-and-Corporate-Set
- Merged PR 14 - arindal1/yolov5-onnx-object-recognition
- Merged PR 19958 - openvinotoolkit/openvino