API for Whisper
E17415
API for Whisper is OpenAI’s cloud-based interface for programmatically accessing its Whisper speech recognition model to transcribe and translate audio.
Aliases (2)
Statements (45)
| Predicate | Object |
|---|---|
| instanceOf |
OpenAI product
→
cloud service → speech recognition API → |
| accessMethod |
HTTP API
→
REST API → |
| authenticationMethod |
bearer token
→
|
| category |
machine learning API
→
speech recognition service → |
| deploymentModel |
cloud-based
→
|
| developer |
OpenAI
→
|
| documentationURL |
https://platform.openai.com/docs
→
|
| inputType |
audio
→
video → |
| intendedAudience |
AI application builders
→
software developers → |
| maintainer |
OpenAI
→
|
| outputType |
text transcription
→
text translation → |
| pricingModel |
usage-based
→
|
| provider |
OpenAI API platform
→
|
| providesAccessTo |
Whisper model
→
|
| relatedTo |
OpenAI Chat Completions API
→
OpenAI Whisper model → |
| requires |
API key
→
internet connection → |
| supportsCapability |
automatic language detection
→
timestamped transcription (segment-level) → transcription of long-form audio → |
| supportsEnvironment |
cloud applications
→
web services → |
| supportsFormat |
common audio formats
→
|
| supportsIntegration |
backend services
→
data processing pipelines → server-side applications → |
| supportsLanguage |
multiple languages
→
|
| supportsOperation |
transcriptions.create
→
translations.create → |
| supportsTask |
speech transcription
→
speech translation → speech-to-text → |
| useCase |
call center transcription
→
meeting transcription → podcast transcription → video captioning → voice note transcription → |
Referenced by (3)
| Subject (surface form when different) | Predicate |
|---|---|
|
OpenAI
→
|
product |
|
API for Whisper
("OpenAI Whisper model")
→
|
relatedTo |
|
Hugging Face Transformers
("Speech2Text")
→
|
supportsModelType |