Skip to main content

Speech model rankings

Compare models within each evaluation task using original scores and configurations.

Sources

Ranked by the upstream word error rate index; lower is better. Provider configurations are shown separately.

Select up to four models to compare their specifications, prices and evidence.

0 of 4 models selected.
12.29 WER %Grok Voice Transcribe 2.0 · SpaceXAI—2026-11-05
22.82 WER %Gemini 3.1 Pro Preview (High) · Google—2026-11-05
32.86 WER %Gemini 2.5 Pro · Google—2026-11-05
43.58 WER %Gemini 3.1 Pro Preview (Low) · Google—2026-11-05
54.07 WER %Whisper Large v3 · fal.ai—2026-11-05
64.53 WER %Whisper Large v3 · Together AI—2026-11-05
74.62 WER %Whisper Large v3 Turbo · Groq—2026-11-05
84.69 WER %Wizper Large v3 · fal.ai—2026-11-05
95.14 WER %Gemini 2.5 Flash · Google—2026-11-05
105.53 WER %Whisper Large v3 Turbo, Telnyx · Telnyx · none—2026-11-05
1110.06 WER %Whisper Large v3 · Replicate—2026-11-05

Page 1 of 1

Frequently asked questions