Start with 45 free minutes of callsTry for free

Speech-to-Text · Multilingual

Hindi

Language

Request a new language

Tell us which language you want added to this benchmark.

Benchmarks

X
Y

WER

Share of words the transcript got wrong.

Sonioxstt-rt-v6Try →8.2%
Sonioxstt-rt-v5Try →8.6%
OpenAIGPT Live TranscribeTry →9.9%
OpenAIGPT-4o TranscribeTry →11.9%
DeepgramNova-3Try →14.0%
OpenAIGPT-4o-mini TranscribeTry →15.9%
AssemblyAIAssemblyAIUniversal-3.5 ProTry →17.4%
ElevenLabsScribe v2 RealtimeTry →18.6%
DeepgramNova-2Try →23.7%
CartesiaInk-WhisperTry →41.6%
0.0%10.0%20.0%30.0%40.0%50.0%

Finalize latency

lower is better

Time from the caller stopping to the finalized transcript, not the first partial — the agent cannot reply until it lands. Measured on English audio; Hindi has no sweep of its own yet.

DeepgramNova-3Try →189ms · 770ms
Sonioxstt-rt-v6Try →315ms · 2.75s
Sonioxstt-rt-v5Try →340ms · 1.33s
AssemblyAIAssemblyAIUniversal-3.5 ProTry →408ms · 908ms
OpenAIGPT Live TranscribeTry →620ms · 770ms
OpenAIGPT-4o-mini TranscribeTry →822ms · 1.09s
OpenAIGPT-4o TranscribeTry →848ms · 1.18s
ElevenLabsScribe v2 RealtimeTry →1.75s · 1.98s
0ms300ms600ms900ms1.20s

p50 p90

Time to first token

lower is better

How long before the first word of the transcript arrives. Measured on English audio; Hindi has no sweep of its own yet.

DeepgramNova-3Try →976ms · 1.98s
AssemblyAIAssemblyAIUniversal-3.5 ProTry →1.01s · 1.51s
Sonioxstt-rt-v5Try →1.53s · 2.04s
OpenAIGPT Live TranscribeTry →1.72s · 2.24s
Sonioxstt-rt-v6Try →1.91s · 2.31s
ElevenLabsScribe v2 RealtimeTry →2.22s · 2.36s
OpenAIGPT-4o-mini TranscribeTry →6.33s · 10.6s
OpenAIGPT-4o TranscribeTry →6.40s · 10.8s
0ms2.00s4.00s6.00s8.00s

p50 p90

Cost

lower is better

$ per 1,000 minutes of audio · vendor list price, the same in every language