Open ASR · AMI-Cleaned WER ↗English short-form; normalization unversioned
13.63% WERopenai/whisper-large-v3
openaiListed Jul 17, 2024
whisper-large-v3
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.
Measured performance
All leaderboards ↗Benchmark results
Word error rate · lower is better
Open ASR · Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned
7.99% WERopenai/whisper-large-v3
Open ASR · Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned
8.35% WERopenai/whisper-large-v3
Open ASR · LS Clean WER ↗English short-form; normalization unversioned
1.56% WERopenai/whisper-large-v3
Open ASR · LS Other WER ↗English short-form; normalization unversioned
3.52% WERopenai/whisper-large-v3
Open ASR · SPGISpeech WER ↗English short-form; normalization unversioned
2.71% WERopenai/whisper-large-v3
Open ASR · URGENT2024 WER ↗English short-form; normalization unversioned
13.73% WERopenai/whisper-large-v3
Open ASR · Voice Arena Monsoon WER ↗English short-form; normalization unversioned
3.95% WERopenai/whisper-large-v3
Open ASR · Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned
4.53% WERopenai/whisper-large-v3
Access & cost
2 quotesPrices across providers
- Input
- $7.50
- Output
- $0.00
DeepInfra
Input audio second
- Rate
- $0.0000075
Model specifications
- Developer
- openai
- Modality
- Audio
- Context
- Not reported
- Maximum output
- Not reported
- Weights
- Open weights
- Provider listed
- Jul 17, 2024
- First discovered
- Oct 16, 2026
Exact identities
- openrouter
openai/whisper-large-v3 - deepinfra
openai/whisper-large-v3 - open-asr
openai%2Fwhisper-large-v3
Sources
Updated Oct 18, 2026
More from openai
View all ↗openaiListed Jan 19
OpenAI: GPT Audio
The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...
128K contextAudio inputTool callingNo reported score
No reported score
Price not listed
openaiListed Jan 19
OpenAI: GPT Audio Mini
A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...
128K contextAudio inputTool callingNo reported score
No reported score
Price not listed
openaiListed Oct 2
whisper-large-v3-turbo
Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper "Robust Speech Recognition via Large-Scale Weak Supervision" by Alec Radford et al.…
Audio inputOpen weights