Speech-to-Text

Time from the caller stopping to the finalized transcript, not the first partial — the agent cannot reply until it lands.

DeepgramNova-3222ms · 576ms

Sonioxstt-rt-v5345ms · 1.33s

CartesiaInk-2556ms · 960ms

InworldRealtime STT-1561ms · 1.09s

AssemblyAIUniversal-3.5 Pro605ms · 1.21s

DeepgramFlux706ms · 1.29s

Smallest AIPulse793ms · 1.08s

OpenAIGPT Transcribe820ms · 1.12s

GladiaSolaria-1837ms · 3.09s

OpenAIGPT-4o-mini Transcribe857ms · 1.17s

OpenAIGPT-4o Transcribe867ms · 1.21s

AlibabaQwen3-ASR873ms · 1.17s

Gradium ASR1.13s · 1.34s

xAIGrok STT1.13s · 1.35s

ModulateVelma 21.21s · 1.41s

ElevenLabsScribe v2 Realtime1.71s · 1.99s

0ms300ms600ms900ms1.20s

p50 p90

What a vendor charges to transcribe a thousand minutes of audio, at its published streaming rate.

$0.00$5.00$10.00$15.00$20.00

$1.00

$2.00

$2.50

$3.00

$3.30

$3.70

$4.50

$4.80

~$5.00

$5.40

$6.00

$6.50

$6.50

$7.50

$9.00

$10.40

$12.50

$16.00

$17.00

ModulateVelma 2Sonioxstt-rt-v5InworldRealtime STT-1OpenAIGPT-4o-mini TranscribexAIGrok STTElevenLabsScribe v2OpenAIGPT TranscribeDeepgramNova-3Smallest AIPulseAlibabaQwen3-ASROpenAIGPT-4o TranscribeDeepgramFluxElevenLabsScribe v2 RealtimeAssemblyAIUniversal-3.5 ProCartesiaInk-2Gradium ASRGladiaSolaria-1GoogleChirp 3OpenAIGPT Live Transcribe