Speech-to-Text Benchmark Results — Word Error Rate (WER %, lower is better)

Methodology: each audio file sent to every provider's production API with default settings. Transcriptions normalized with OpenAI Whisper text normalizer before WER computation. 74 hours of audio across 7 datasets. Full methodology: https://github.com/gladiaio/normalization

Columns: WER = Word Error Rate (%, lower is better) · Perfect = number of files with 0% WER · High WER = files with WER above 50% · RTFx = Real-Time Factor multiplier (higher = faster than real-time)

Switchboard — Conversational Speech

Common Voice 24 — Clean Audio (Multilingual)

VoxPopuli — Formal Discourse (European Parliament)

Earnings22 Full — Financial Calls (Long-form, single file)

Earnings22 Cleaned AA — Financial Calls (Curated by Artificial Analysis)

Multilingual LibriSpeech — Audiobooks (5 languages, average)

Multilingual LibriSpeech — WER by Language (%)

Pipecat STT Benchmark — Real-Time Streaming

Speaker Diarization Benchmark — DIHARD III — Diarization Error Rate (DER %, lower is better)