Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of OpenAI: GPT Audio, abr-ai/niagara-38m-batch.en
2 modelsopenaiOpenAI: GPT AudioRemove ×abr-aiabr-ai/niagara-38m-batch.enRemove ×
What’s differentThe 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...0.038B parameters · 1 language · Encoder: State-space model · Decoder: CTC
DateJan 19, 2026ListedOct 17, 2026Discovered
Listed rateSee provider quotesSee provider quotes
Provider endpoints0 endpoints →0 endpoints →
AMI-Cleaned WER ↗English short-form; normalization unversionedNot reported13.87% WER ↗abr-ai/niagara-38m-batch.enLeaderboard entry
Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversionedNot reported12.94% WER ↗abr-ai/niagara-38m-batch.enLeaderboard entry
Gigaspeech-Cleaned WER ↗English short-form; normalization unversionedNot reported11.38% WER ↗abr-ai/niagara-38m-batch.enLeaderboard entry
LS Clean WER ↗English short-form; normalization unversionedNot reported3.81% WER ↗abr-ai/niagara-38m-batch.enLeaderboard entry
LS Other WER ↗English short-form; normalization unversionedNot reported9.28% WER ↗abr-ai/niagara-38m-batch.enLeaderboard entry
SPGISpeech WER ↗English short-form; normalization unversionedNot reported3.08% WER ↗abr-ai/niagara-38m-batch.enLeaderboard entry
URGENT2024 WER ↗English short-form; normalization unversionedNot reported22.88% WER ↗abr-ai/niagara-38m-batch.enLeaderboard entry
Voice Arena Monsoon WER ↗English short-form; normalization unversionedNot reported10.41% WER ↗abr-ai/niagara-38m-batch.enLeaderboard entry
Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversionedNot reported5.16% WER ↗abr-ai/niagara-38m-batch.enLeaderboard entry
Context window128K—
Max output16.4K—
Parameters—0.038B
Tool callingSupportedNot reported
Structured outputSupportedNot reported
Audio inputSupportedSupported
TranscriptionNot reportedSupported

Add another model

Search all models →