Kurtis E1
Collection
The Empathetic Assistant.
•
11 items
•
Updated
ethicalabs.ai
Enterprise
non-profit
AI & ML interests
Building practical, ethical and sustainable AI/ML projects.
Recent Activity
View all activity
ethicalabs's activity
mrs83
updated
a
collection
24 days ago
Kurtis E1: A Voice for Empathy in the Tapestry of Consciousness
#1 opened 24 days ago
by
mrs83
mrs83
updated
a
model
24 days ago
mrs83
updated
a
Space
25 days ago
mrs83
updated
a
model
26 days ago
mrs83
published
a
model
27 days ago
surprisingly good
1
#1 opened 28 days ago
by
mrs83
Improve language tag
1
#1 opened about 2 months ago
by
lbourdois
mrs83
updated
a
model
about 1 month ago
mrs83
updated
a
collection
about 1 month ago
mrs83
published
a
model
about 1 month ago
mrs83
updated
a
collection
about 1 month ago
mrs83
updated
a
model
about 2 months ago
mrs83
published
a
model
about 2 months ago
mrs83
updated
2
datasets
about 2 months ago
Post
1761
To developers: Build opt-in systems.
To policymakers: Legislate data transparency.
To artists: Unionize.
To users: Demand ethical tools.
To policymakers: Legislate data transparency.
To artists: Unionize.
To users: Demand ethical tools.
-
- 1 reply
Post
3219
🚀 Just released a PoC: Kurtis-E1 MLX Voice Agent
An offline, privacy-first voice assistant built for macOS (Apple Silicon), designed for empathetic, short-form interactions.
🧠 Powered by:
- Whisper (via MLX) for speech-to-text: https://pypi.org/project/mlx-whisper/
- Kurtis-E1 (a custom SmolLM2 LLM) via Ollama
- Coqui-TTS XTTSv2 for multilingual TTS
- Optional translation layer via TowerInstruct-13B-v0.1 for non-English voice input/output: Unbabel/TowerInstruct-13B-v0.1
🎧 Everything runs entirely on-device (Mac Mini M4 Max - 24gb) — no cloud, no remote API calls, no data leakage.
💡 Code is fully handcrafted (no AI-generated code), and designed to showcase what’s possible with local models, even on laptops.
🛠️ Open to contributions, ideas (e.g., LM Studio for MLX inference, MLX worker subprocess, optimize for latency and VRAM usage).
👉 Video demo (Italian): https://www.youtube.com/watch?v=8-1PcmUStaI
PoC: https://github.com/ethicalabs-ai/Kurtis-E1-MLX-Voice-Agent
Kurtis-E1: ethicalabs/kurtis-e1-67a9148e0836885c44c7902c
Kurtis-E1 WebGPU: ethicalabs/Kurtis-E1-WebGPU
An offline, privacy-first voice assistant built for macOS (Apple Silicon), designed for empathetic, short-form interactions.
🧠 Powered by:
- Whisper (via MLX) for speech-to-text: https://pypi.org/project/mlx-whisper/
- Kurtis-E1 (a custom SmolLM2 LLM) via Ollama
- Coqui-TTS XTTSv2 for multilingual TTS
- Optional translation layer via TowerInstruct-13B-v0.1 for non-English voice input/output: Unbabel/TowerInstruct-13B-v0.1
🎧 Everything runs entirely on-device (Mac Mini M4 Max - 24gb) — no cloud, no remote API calls, no data leakage.
💡 Code is fully handcrafted (no AI-generated code), and designed to showcase what’s possible with local models, even on laptops.
🛠️ Open to contributions, ideas (e.g., LM Studio for MLX inference, MLX worker subprocess, optimize for latency and VRAM usage).
👉 Video demo (Italian): https://www.youtube.com/watch?v=8-1PcmUStaI
PoC: https://github.com/ethicalabs-ai/Kurtis-E1-MLX-Voice-Agent
Kurtis-E1: ethicalabs/kurtis-e1-67a9148e0836885c44c7902c
Kurtis-E1 WebGPU: ethicalabs/Kurtis-E1-WebGPU
-
- 3 replies
mrs83
updated
a
dataset
3 months ago