Model comparison
Moonshine Base vs Gemini 2.5 Pro
Capability radar, value bars, and side-by-side posture.
Moonshine Base
Not scored
value score
Gemini 2.5 Pro
93
value score
Moonshine Base ctx
—
Gemini 2.5 Pro ctx
1.0M
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- Gemini 2.5 Pro93
Attribute tape
| Field | Moonshine Base | Gemini 2.5 Pro |
|---|---|---|
| Developer | Vokra | Google DeepMind |
| Context | — | 1.0M |
| Modalities | Text, Code, Image, Audio, Video | |
| Openness | — | Proprietary Model |
| Speed | — | — |
| Price | — | $1.25/1M in · $10/1M out |
| Value score | — | 93 |
| Summary | Moonshine Base is a lightweight English automatic speech recognition (ASR) model from Useful Sensors / Vokra, optimized for real-time, low-latency transcription on resource-constrained and edge devices. It uses an encoder-decoder Transformer with RoPE and is reported to outperform similarly sized Whisper models on word error rate while requiring less compute. | Google frontier multimodal model. |