Request a new model

Tell us which model you want measured. We review every request.

Speech-to-Text

WER

Route
ElevenLabsScribe v2 Realtime9.6%
AssemblyAIAssemblyAIUniversal-3.5 Pro10.4%
Smallest AISmallest AIPulse11.0%
OpenAIGPT Live Transcribe11.3%
xAIGrok STT11.3%
MetaMetaMuse Voice Transcribe11.7%
InworldInworldRealtime STT-111.8%
AlibabaQwen3-ASR12.2%
ModulateModulateVelma 212.3%
CartesiaInk-212.5%
GoogleGemini 3.5 Transcribe Live13.1%
Sonioxstt-rt-v513.1%
OpenAIGPT Transcribe15.1%
DeepgramNova-315.1%
GoogleChirp 317.3%
DeepgramFlux17.8%
GladiaSolaria-118.2%
OpenAIGPT-4o-mini Transcribe18.5%
GradiumASR22.9%
OpenAIGPT-4o Transcribe31.9%
0.0%10.0%20.0%30.0%40.0%

Finalize latency

Region

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

DeepgramNova-3222ms · 576ms
MetaMetaMuse Voice Transcribe261ms · 549ms
Sonioxstt-rt-v5345ms · 1.33s
CartesiaInk-2556ms · 960ms
InworldInworldRealtime STT-1561ms · 1.09s
AssemblyAIAssemblyAIUniversal-3.5 Pro605ms · 1.21s
DeepgramFlux706ms · 1.29s
Smallest AISmallest 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
GradiumASR1.13s · 1.34s
xAIGrok STT1.13s · 1.35s
ModulateModulateVelma 21.21s · 1.41s
GoogleGemini 3.5 Transcribe Live1.29s · 1.58s
ElevenLabsScribe v2 Realtime1.71s · 1.99s
0ms300ms600ms900ms1.20s

p50 p90

Time to first token

Region
DeepgramFlux792ms · 1.49s
DeepgramNova-31.02s · 2.03s
xAIGrok STT1.04s · 2.01s
AssemblyAIAssemblyAIUniversal-3.5 Pro1.10s · 1.61s
InworldInworldRealtime STT-11.13s · 1.93s
ModulateModulateVelma 21.48s · 1.49s
GladiaSolaria-11.49s · 2.61s
Sonioxstt-rt-v51.53s · 2.03s
MetaMetaMuse Voice Transcribe1.60s · 2.12s
GoogleGemini 3.5 Transcribe Live1.74s · 2.31s
CartesiaInk-21.76s · 2.37s
ElevenLabsScribe v2 Realtime2.21s · 2.32s
Smallest AISmallest AIPulse2.27s · 2.29s
GradiumASR2.44s · 2.95s
OpenAIGPT-4o Transcribe6.32s · 10.6s
OpenAIGPT-4o-mini Transcribe6.36s · 10.6s
OpenAIGPT Transcribe6.37s · 10.6s
AlibabaQwen3-ASR6.79s · 7.44s
0ms2.00s4.00s6.00s8.00s

p50 p90

Cost

lower is better

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
$1.70
$2.00
$2.50
$3.00
$3.00
$3.30
$3.70
$4.50
$4.80
~$5.00
$5.40
$6.00
$6.50
$6.50
$7.50
$9.00
~$9.00
$10.40
$12.50
$16.00
$17.00
ModulateModulateVelma 2MMicrosoftMAI-Transcribe-2Sonioxstt-rt-v5InworldInworldRealtime STT-1OpenAIGPT-4o-mini TranscribeMetaMetaMuse Voice TranscribexAIGrok STTElevenLabsScribe v2OpenAIGPT TranscribeDeepgramNova-3Smallest AISmallest AIPulseAlibabaQwen3-ASROpenAIGPT-4o TranscribeDeepgramFluxElevenLabsScribe v2 RealtimeAssemblyAIAssemblyAIUniversal-3.5 ProCartesiaInk-2GoogleGemini 3.5 Transcribe LiveGradiumASRGladiaSolaria-1GoogleChirp 3OpenAIGPT Live Transcribe

FAQ

Which STT API has the lowest latency for phone calls?
AssemblyAI Universal-3.5 Pro finalizes a turn in 66ms (p50, end of speech to final transcript, us-east4), the fastest measured on the board. Soniox stt-rt-v5 is next at 78ms.
What is the most accurate speech-to-text API on the streaming path?
AssemblyAI Universal-3.5 Pro measured 2.0% WER over the live streaming socket, the lowest streaming error rate on the board, and it is the rare model that gives up nothing against its own 2.0% batch WER.
Why is streaming WER higher than batch WER?
Batch uploads the whole clip; streaming transcribes it live, and most models lose accuracy on that path. Deepgram Nova-3 measured 12.0% WER batch against 12.9% streaming on the same clips.
What is the cheapest streaming STT API?
Modulate Velma 2 lists at $0.001 per minute of audio (5.4% streaming WER) and Soniox stt-rt-v5 at $0.002 (7.3% streaming WER), the two lowest rates on the board.
What does end-of-turn latency mean for a voice agent?
It is the wait between the caller finishing and the final transcript arriving, and the agent cannot reply until it lands. Measured p50s on the board span 66ms (AssemblyAI Universal-3.5 Pro) to 1.22s (Google Gemini 3.5 Transcribe Live).