There has recently been a few discussions about speeding up audio files to save on transcription costs, so I have written a benchmark to show how this affects the WER (word error rate). Before we jump into the results, here’s a disclaimer: Disclaimer: All benchmarks on speech-to-text model’s are d…

How Audio Speed Affects Transcription Accuracy: Benchmark Insights

Universus August 15, 2024, 10:38am 17

How about slowing the speed ?
How does it affect the WER ?

How can we measure the WER ?

Topic		Replies	Views
A crazy idea or it's feasible: Technique that saves 30% on Transcribe Costs Community whisper , openai , transcribe , cost , speech	32	2973	May 5, 2024
Extracting Transcription Without Using input_audio.input_transcription in OpenAI API API realtime , api-realtime	10	275	March 11, 2025
API model whisper - Real cost API	19	62819	December 28, 2023
Whisper - opaque charges? API whisper	12	1666	October 28, 2024
TTS API service usability API tts	17	6808	December 16, 2023