Speech to Text (ASR): Leaderboard & Comparison
Analysis and comparison of Speech to Text transcription models & API providers. Artificial Analysis has analyzed speech to text models and hosting providers across different characteristics including their word error rate (lower is better), speed and price. Speed is represented by 'Speed Factor' which is the number of audio seconds transcribed per second (higher is better). For further details, see our methodology page.
Speech-to-text models & providers compared: Whisper (L, v2), OpenAI, Universal-1, AssemblyAI, Speechmatics Standard, Whisper (L, v2), Azure, Speechmatics Enhanced, Nano, Assembly AI, Incredibly Fast Whisper, Replicate, Whisper (L, v2), Replicate, Nova-2, Deepgram, Base, Deepgram, Whisper (L, v3), Replicate, WhisperX, Replicate, Whisper (L v2), Deepgram, Gladia, Whisper (M), Replicate, Whisper (S), Replicate, Whisper (L, v3), fal.ai, Amazon Transcribe, Rev AI, and Chirp, Google.
Highlights
Word error rate
Word error rate: % of words transcribed incorrectly, Lower is better
Speed Factor
Speed factor: Input audio seconds transcribed per second, Higher is better
Price
Price: USD per 1000 minutes of audio, Lower is better
Summary analysis
Word Error Rate vs. Price
Word error rate: % of words transcribed incorrectly, Price: USD per 1000 minutes of audio
Most attractive quadrant
Size represents Speed factor: Input audio seconds transcribed per second
Word Error Rate: Percentage of words incorrect in the transcription.
Price: Cost in USD per 1000 minutes of audio transcribed. Reflects the pricing model of the transcription service or software.
Artificial Analysis' independent evaluation is based on Common Voice v16.1, Mozilla's leading open-source speech to text dataset. Further detail present on methodology page.
Word Error Rate vs. Speed Factor
Word error rate: % of words transcribed incorrectly, Speed factor: Input audio seconds transcribed per second
Most attractive quadrant
Size represents Price: USD per 1000 minutes of audio
Word Error Rate: Percentage of words incorrect in the transcription.
Artificial Analysis' independent evaluation is based on Common Voice v16.1, Mozilla's leading open-source speech to text dataset. Further detail present on methodology page.
Speed Factor: Audio file seconds transcribed per second of processing time. Higher factor indicates faster transcription speed.
Artificial Analysis' measurements are based on a audio duration of 10 minutes. Speed Factor may vary for other durations, particuarly for very short durations (under 1 minute).
Speed Factor vs. Price
Speed factor: Input audio seconds transcribed per second, Price: USD per 1000 minutes of audio
Most attractive quadrant
Speed Factor: Audio file seconds transcribed per second of processing time. Higher factor indicates faster transcription speed.
Artificial Analysis' measurements are based on a audio duration of 10 minutes. Speed Factor may vary for other durations, particuarly for very short durations (under 1 minute).
Price: Cost in USD per 1000 minutes of audio transcribed. Reflects the pricing model of the transcription service or software.
Quality
Word Error Rate
Word error rate: % of words transcribed incorrectly, Lower is better
Word Error Rate: Percentage of words incorrect in the transcription.
Artificial Analysis' independent evaluation is based on Common Voice v16.1, Mozilla's leading open-source speech to text dataset. Further detail present on methodology page.
Speed
Speed Factor
Speed factor: Input audio seconds transcribed per second, Higher is better
Speed Factor: Audio file seconds transcribed per second of processing time. Higher factor indicates faster transcription speed.
Artificial Analysis' measurements are based on a audio duration of 10 minutes. Speed Factor may vary for other durations, particuarly for very short durations (under 1 minute).
Speed Factor, Variance
Speed factor: Input audio seconds transcribed per second, Results by percentile, Higher is better
Median, Other points represent 5th, 25th, 75th, 95th Percentiles respectively
Speed Factor: Audio file seconds transcribed per second of processing time. Higher factor indicates faster transcription speed.
Artificial Analysis' measurements are based on a audio duration of 10 minutes. Speed Factor may vary for other durations, particuarly for very short durations (under 1 minute).
Boxplot: Shows variance of measurements
Speed Factor, Over Time
Speed factor: Input audio seconds transcribed per second, Higher is better
Speed Factor: Audio file seconds transcribed per second of processing time. Higher factor indicates faster transcription speed.
Artificial Analysis' measurements are based on a audio duration of 10 minutes. Speed Factor may vary for other durations, particuarly for very short durations (under 1 minute).
Over time measurement: Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.
Price
Price
Price: USD per 1000 minutes of audio, Lower is better
Price: Cost in USD per 1000 minutes of audio transcribed. Reflects the pricing model of the transcription service or software.
For providers which do not price based on audio duration and rather on processing time (incl. Replicate, fal), we have calculated an indicative per minute price based on processing time expected per minute of audio. Further detail present on methodology page.
Summary of key metrics & further information
| Host | Model | Whisper version | Footnotes | Word Error Rate (%) | Median Speed Factor | Price (USD per 1000 minutes) | Further Details |
|---|---|---|---|---|---|---|---|
 OpenAI | Whisper (large-v2) | large-v2 | 9.2% | 35.5 | 6.00 | ||
 Microsoft Azure | Whisper (large-v2) | large-v2 | 9.2% | 37.3 | 6.00 | ||
 Replicate | Incredibly Fast Whisper | large-v3 | 8.2% | 43.6 | 1.49 | ||
| Replicate | Whisper (large-v2) | large-v2 | 9.2% | 2.4 | 3.47 | ||
| Replicate | Whisper (large-v3) | large-v3 | 8.4% | 2.7 | 4.23 | ||
| Replicate | WhisperX | large-v3 | 9.7% | 12.3 | 1.09 | ||
| Replicate | Whisper (medium) | medium | 10.7% | 5.4 | 2.68 | ||
| Replicate | Whisper (small) | small | 15.0% | 18.1 | 1.37 | ||
 fal.ai | Whisper, fal.ai | large-v3 | 8.2% | 109.6 | 1.15 | ||
 AssemblyAI | AssemblyAI (Universal-1) | 7.2% | 43.0 | 6.17 | |||
| AssemblyAI | Nano | 10.5% | 54.0 | 2.00 | |||
 Speechmatics | Speechmatics Standard | 10.5% | 17.7 | 13.33 | |||
| Speechmatics | Speechmatics Enhanced | 6.5% | 9.2 | 17.33 | |||
 Deepgram | Nova-2 | 11.5% | 178.5 | 4.30 | |||
| Deepgram | Base | 22.9% | 207.0 | 12.50 | |||
| Deepgram | Whisper Large v2 | large-v2 | 9.2% | 61.0 | 4.80 | ||
 Gladia | Gladia | whisper-v2 based | 10.7% | 10.0 | 10.20 | ||
 Amazon Bedrock | Amazon Transcribe | 9.9% | 23.8 | 24.00 | |||
 Rev AI | Rev AI | 18.1% | 9.0 | 20.00 | |||
 Google | Cloud Speech-To-Text (Chirp) | 10.8% | 14.1 | 16.00 |