| ▲ | mnbbrown 10 hours ago | |
Ran it over our internal dataset of ~250 recordings of people saying british postcodes (all kinds of accents, etc) - it's competitive for sure! Soniox (stt-async-v4): 176/248 (71.0%) ElevenLabs (scribe_v2): 170/248 (68.5%) AssemblyAI (universal-3-pro): 166/248 (66.9%) Deepgram (nova-3): 158/248 (63.7%) AssemblyAI (universal-2): 148/248 (59.7%) Cohere (transcribe-03-2026): 148/248 (59.7%) Speechmatics (enhanced): 134/248 (54.0%) P.s. how do I get this to render correctly on here? | ||
| ▲ | yorwba an hour ago | parent | next [-] | |
Is the human baseline 248/248? | ||
| ▲ | jilijeanlouis 5 hours ago | parent | prev | next [-] | |
did you try gladia: ranking #1 on STT blind test https://compare-stt.com/ | ||
| ▲ | Bolwin 9 hours ago | parent | prev [-] | |
Try two newlines between each one | ||