Voice & Conversational Interfaces benchmarks
How performance is measured at the frontier · as of 2026-07-07 · 5 benchmarks
Accuracy
Word Error Rate
% WERTranscription errors across the Open ASR test suite — lower is better.
↓ lower is better·Open ASR Leaderboard
- #013.3%
- #02
nvidia/nemotron-speech-streaming-en-0.6b 4.0% - #03
microsoft/azure-speech-06-2026 5.2% - #04
OpenMOSS-Team/MOSS-Transcribe-preview-2B 5.3% - #055.4%
- #06
bosonai/higgs-audio-v3-stt 5.4% - #075.5%
- #08
bosonai/higgs-audio-v3-8b-stt-v2 5.5% - #09
nvidia/nemotron-3.5-asr-streaming-0.6b 5.5% - #105.6%
- #115.6%
- #12
ibm-granite/granite-speech-4.1-2b 5.6%
Speed
Throughput (RTFx)
× real-timeAudio-seconds transcribed per second of compute — higher is faster.
↑ higher is better·Open ASR Leaderboard
- #01
nvidia/stt_en_conformer_ctc_small 6,258× - #02
nvidia/parakeet-tdt_ctc-110m 6,119× - #03
nvidia/parakeet-tdt-0.6b-v3 6,098× - #04
nvidia/parakeet-tdt-0.6b-v2 6,038× - #05
nvidia/stt_en_fastconformer_transducer_large 6,033× - #06
nvidia/stt_en_fastconformer_ctc_large 6,027× - #075,884×
- #08
nvidia/stt_en_conformer_ctc_large 5,732× - #09
nvidia/stt_en_conformer_transducer_small 5,557× - #10
nvidia/parakeet-rnnt-0.6b 5,407× - #115,015×
- #124,529×
Naturalness
- #011,568
- #021,565
- #031,564
- #041,555
- #051,547
- #061,537
- #071,533
- #081,531
- #091,530
- #101,530
- #111,530
- #121,528
Economics
Transcription cost
$ / minutePublished speech-to-text API price per minute — lower is cheaper.
↓ lower is better·LiteLLM (open pricing)
- #01$0.0007
- #02$0.0020
- #03$0.0037
- #04$0.0043
- #05$0.0060
- #06$0.0060
TTS cost
$ / 1M charsPublished text-to-speech price per million characters — lower is cheaper.
↓ lower is better·LiteLLM (open pricing)
- #01$4
- #02$15
- #03$16
- #04$30
- #05$30
- #06$50
- #07$60
- #08$180
