antonios_makro

Joined 1 year ago

Karma

1

Submissions

26

Member since

Feb 3

Building real-time, on-device agentic AI with a face · Voice + avatar + action @ myned.ai

View on Hacker News

Recent submissions

Show HN: Greek and Cypriot Greek TTS that runs faster than real time on CPU huggingface.co

1 antonios_makro 1 month ago 0 comments

Show HN: We gave Hugging Face's realtime voice demo a face and it runs on a CPU huggingface.co

2 antonios_makro 3 months ago 0 comments

Comment · 4 months ago

This dataset powers our v2 version so not published yet, the v1 with no strong facial expression is in many places ..check myned.ai avatar, or nyxclaw.ai

Comment · 4 months ago

datasets: CREMA-D / RAVDESS / TESS / JL Corpus models: NVIDIA A2F - 3D, LAM audio2 expression, check the HF page for links

Show HN: Open dataset for distilling GPU audio2face models to CPU students huggingface.co

3 antonios_makro 4 months ago 4 comments

Comment · 4 months ago

Any day now, we have some issues with apple dev support (what a surprise) but we dealing with it, keep an eye on nyxclaw.ai

Comment · 4 months ago

Thanks, we releasing hermes support soon, keep an eye on nyxclaw.ai

Comment · 4 months ago

thanks, check our repo: https://github.com/myned-ai/nyxclaw, everything is there ..

Comment · 4 months ago

Give any AI agent a real-time face and voice. Open source, runs on your machine, no GPU required.

Show HN: Every Claw Deserves a Face nyxclaw.ai

8 antonios_makro 4 months ago 8 comments

Comment · 5 months ago

The bottleneck isn't managing the 'army', it's the interaction latency of a single agent. An AI 'employee' that makes a customer wait 800ms for a voice response feels broken. Getting that full STT->LLM->TTS->render loop under 250ms is the real barrier. This is the problem we're focused on with Nyx: giving the agent a real-time face and voice. An agent that can't hold a conversation isn't much of an employee. Any feedback appreciated: NyxClaw.ai