Speech-to-Text

Time from the last spoken word to the final transcript, decided by the model itself.

MetaMuse Voice Transcribe301ms · 584ms

Sonioxstt-rt-v5489ms · 2.40s

AssemblyAIUniversal-3.6 Pro589ms · 1.58s

AssemblyAIUniversal-3.5 Pro606ms · 1.62s

DeepgramFlux Multilingual654ms · 1.36s

NariQwen3-ASR Fast684ms · 965ms

DeepgramNova-3771ms · 1.21s

DeepgramFlux773ms · 1.48s

ElevenLabsScribe v2 Realtime793ms · 1.06s

OpenAIGPT-4o mini Transcribe926ms · 1.35s

Smallest AIPulse958ms · 1.45s

GladiaSolaria-11.09s · 1.59s

GradiumASR1.22s · 1.35s

ModulateVelma 21.25s · 1.54s

OpenAIGPT-4o Transcribe1.28s · 1.70s

xAIGrok Voice Transcribe 2.01.35s · 1.75s

xAIGrok Voice Transcribe 1.01.40s · 1.95s

SpeechmaticsStandard1.45s · 1.81s

InworldRealtime STT-11.90s · 2.71s

0ms500ms1.00s1.50s2.00s2.50s

p50 p90

Time from the caller starting to speak to the first word of the live transcript.

AzureMAI-Transcribe-2 Streaming241ms · 342ms

DeepgramFlux Multilingual506ms · 1.65s

DeepgramFlux641ms · 1.19s

GladiaSolaria-1671ms · 1.20s

SpeechmaticsStandard690ms · 1.05s

MetaMuse Voice Transcribe728ms · 1.16s

AssemblyAIUniversal-3.6 Pro775ms · 974ms

AssemblyAIUniversal-3.5 Pro775ms · 973ms

Sonioxstt-rt-v5786ms · 1.27s

DeepgramNova-3885ms · 1.45s

InworldRealtime STT-1942ms · 1.02s

OpenAIGPT Realtime Whisper987ms · 1.27s

OpenAIGPT Live Transcribe988ms · 1.13s

xAIGrok Voice Transcribe 1.0989ms · 1.10s

xAIGrok Voice Transcribe 2.0995ms · 1.18s

Smallest AIPulse1.04s · 2.01s

CartesiaInk-21.19s · 1.61s

ModulateVelma 21.38s · 1.47s

NariQwen3-ASR Fast1.65s · 1.74s

GradiumASR1.65s · 2.43s

ElevenLabsScribe v2 Realtime2.02s · 2.19s

OpenAIGPT-4o mini Transcribe2.91s · 6.12s

OpenAIGPT-4o Transcribe4.72s · 8.46s

0ms1.00s2.00s3.00s4.00s5.00s

p50 p90

Time from a word being spoken to it appearing in the live transcript for good.

AzureMAI-Transcribe-2 Streaming114ms · 515ms

DeepgramFlux Multilingual180ms · 715ms

DeepgramFlux190ms · 586ms

SpeechmaticsStandard403ms · 1.07s

MetaMuse Voice Transcribe486ms · 716ms

Sonioxstt-rt-v5496ms · 739ms

InworldRealtime STT-1583ms · 1.86s

DeepgramNova-3583ms · 1.72s

AssemblyAIUniversal-3.5 Pro803ms · 2.52s

AssemblyAIUniversal-3.6 Pro815ms · 2.71s

ModulateVelma 2896ms · 2.35s

NariQwen3-ASR Fast901ms · 2.04s

ElevenLabsScribe v2 Realtime945ms · 1.97s

Smallest AIPulse1.17s · 1.98s

CartesiaInk-21.22s · 1.71s

GradiumASR1.48s · 1.66s

GladiaSolaria-11.50s · 3.98s

xAIGrok Voice Transcribe 2.01.89s · 10.22s

xAIGrok Voice Transcribe 1.02.08s · 8.91s

OpenAIGPT-4o mini Transcribe2.47s · 5.29s

OpenAIGPT-4o Transcribe3.43s · 7.18s

OpenAIGPT Realtime Whisper3.96s · 11.28s

OpenAIGPT Live Transcribe4.02s · 11.34s

0ms1.00s2.00s3.00s4.00s5.00s

p50 p90

Words the live transcript takes back, per word in the final transcript.

GradiumASR0%

CartesiaInk-20%

MetaMuse Voice Transcribe0%

Smallest AIPulse0%

OpenAIGPT-4o Transcribe3%

OpenAIGPT-4o mini Transcribe5%

OpenAIGPT Realtime Whisper6%

OpenAIGPT Live Transcribe10%

Sonioxstt-rt-v513%

NariQwen3-ASR Fast22%

ElevenLabsScribe v2 Realtime29%

InworldRealtime STT-130%

DeepgramNova-333%

ModulateVelma 233%

SpeechmaticsStandard35%

AssemblyAIUniversal-3.6 Pro35%

AssemblyAIUniversal-3.5 Pro36%

AzureMAI-Transcribe-2 Streaming37%

DeepgramFlux40%

DeepgramFlux Multilingual41%

xAIGrok Voice Transcribe 2.064%

xAIGrok Voice Transcribe 1.083%

GladiaSolaria-1156%

0%40%80%120%160%

Published list price per thousand minutes; batch-only models show their batch rate.

$0.00$5.00$10.00$15.00$20.00

$0.83

$1.00

$1.67

$2.00

$2.00

$2.10

$2.50

$2.50

$2.50

$2.67

$3.00

$3.00

$3.30

$3.30

$3.70

$4.00

$4.00

$4.50

$4.80

$6.00

$6.00

$6.50

$6.50

$7.17

$7.50

$7.50

$7.80

$9.00

$10.40

$12.50

$17.00

$17.00

ModulateVelma 2NariQwen3-ASRAzureMAI-Transcribe-2NariQwen3-ASR FastSonioxstt-rt-v5AlibabaQwen3-ASR FlashInworldRealtime STT-1AssemblyAIUniversal-Streaming EnglishAssemblyAIUniversal-Streaming MultilingualSpeechmaticsLinden 1MetaMuse Voice TranscribeOpenAIGPT-4o mini TranscribexAIGrok Voice Transcribe 1.0xAIGrok Voice Transcribe 2.0ElevenLabsScribe v2Smallest AIPulseSpeechmaticsStandardOpenAIGPT TranscribeDeepgramNova-3OpenAIGPT-4o TranscribeFish AudioTranscribe 1 ProElevenLabsScribe v2 RealtimeDeepgramFluxSpeechmaticsEnhancedAssemblyAIUniversal-3.6 ProAssemblyAIUniversal-3.5 ProDeepgramFlux MultilingualCartesiaInk-2GradiumASRGladiaSolaria-1OpenAIGPT Live TranscribeOpenAIGPT Realtime Whisper