Hold a key, talk, and your words type into any Mac app, all on-device.
AI runs online
not yet reviewed by publik
Spokesman
open source · on publik
Prices are for one typical use: one request of about 1,500 words sent and 375 words back. Quality is the Artificial Analysis Intelligence Index v4.3.2 (higher is better).
Not checked yet: publik has not read whether Spokesman can run its AI on your computer.
| Model | Quality | Per 1,000 uses |
|---|---|---|
| On your computer (Ollama, 4-bit download size) | ||
| Granite 4.2 3B2.2 GB | 9 | $0 |
| Phi-4 Mini2.5 GB | 6 | $0 |
| Llama 3.1 8B4.9 GB | 7 | $0 |
| gpt-oss 20B14 GB | 9 | $0 |
| Gemma 4 31B20 GB | 19* | $0 |
| Qwen3.5 35B-A3B24 GB | 19* | $0 |
| publik API | ||
| publik-fastGLM-5.3 Flash | 42 | $1.00 |
| publik-balancedMiMo-V2.6-Pro · Spokesman | 46 | $10.00 |
| publik-smartGPT-5.6 Sol | 47 | $18.00 |
Quality: Artificial Analysis Intelligence Index v4.3.2, read 2026-09-22; * = estimated by Artificial Analysis. Sizes: the Ollama library, read 2026-09-22. publik API prices: publik's published tier prices. A local model's speed depends on your computer.
Every step written out, for people who have never opened a terminal. Pick the setup you have.