Skip to main content Link Menu Expand (external link) Document Search Copy Copied

The AI can distinguish between different speakers and label them throughout the transcript. How to Install Speech to Text v12.0

| Feature | Speech to Text v11 (2022) | | | :--- | :--- | :--- | | Time to transcribe (1 hour, 8 tracks) | 12 minutes | 4 minutes | | Speaker ID accuracy (2 speakers) | 78% | 94% | | Punctuation accuracy | Fair (misses question marks) | Excellent (contextual commas) | | Memory footprint | 1.2 GB | 800 MB (optimized) |

: