OpenAI · Audio
Whisper models: Versions, specs, GPU requirements & hosting
OpenAI Whisper provides a widely deployed speech-recognition checkpoint line for multilingual transcription and translation.
Overview and history
Whisper is an official OpenAI model family represented here through independently verified release, checkpoint, license, runtime and hardware evidence. OpenAI Whisper provides a widely deployed speech-recognition checkpoint line for multilingual transcription and translation. Current public releases are grouped by the Speech Recognition tracks so sibling sizes and specialist branches are not presented as false chronological generations.
FusionPointAI currently tracks 1 certified public Whisper releases. The catalogue preserves release dates and evaluates Current, Recent, Previous and Legacy status within each model track rather than by database insertion order.
Multilingual ASR
Timestamped transcription
Broad runtime ecosystem
Architecture and model range
This Audio and speech family has 1 source-certified public releases. Architecture, parameter counts, and pipeline details are shown only when the official source publishes them; language-model-only context and KV-cache assumptions are not applied.
Public releases1
Model tracks1
Current generationWhisper Large v3 Turbo
Last verified2026-08-26T00:00:00.000000Z
Generations, tracks and variants
General
Deployment ecosystem
Choose a specific Whisper release and certified checkpoint before sizing hardware. FusionPointAI rejects unknown runtime configurations and applies workload-specific memory rules before separating compatible hardware from rentable inventory.
Validate the exact checkpoint, license, runtime, precision, input and output dimensions, batch size, and GPU memory. Resource sizing uses rules appropriate to Audio and speech workloads.
Common use cases
Private Audio and speech workloads
Controlled model evaluation
Production deployment planning
License overview
Licenses are certified per release, not inferred from the provider. Review the release page before commercial deployment because terms can differ between generations and variants.
Commercial-use status is a source-backed catalogue classification, not legal advice. Follow the linked official license and attribution requirements.
Release timeline
Frequently asked questions
Which Whisper release is current?
Current releases are Whisper Large v3 Turbo, evaluated within their respective tracks.
Can Whisper be self-hosted?
Only releases with a verified official checkpoint and supported runtime configuration are presented as deployable.
Which GPU should run Whisper?
GPU selection depends on the exact variant, checkpoint precision, context length and concurrency; use the release hardware recommendations rather than the family name alone.
Official references
Last verified: 2026-08-26