All models
controllable

AuK-Flash

MIT

Distilled four-step speech generation and editing

Evaluate lower-latency speech editing against the base AuK model. Four-step inference is a publisher capability claim, not an OpenSpeech speed measurement. Reference rights and deployment behavior require task-specific review.

Hear AuK-Flash

Standardized samples are pending for this release. See the official sources below for the author’s demo.

AuK-Flash · Samples pending · Same three scripts across the directory.

Best for: Evaluate lower-latency speech editing against the base AuK model.

Permissive model license: Four-step inference is a publisher capability claim, not an OpenSpeech speed measurement. Reference rights and deployment behavior require task-specific review.

Code: MIT. Weights: MIT. License sources checked 2026-09-20. Source 1Source 2

Before you choose: Four-step inference is a publisher capability claim, not an OpenSpeech speed measurement. Reference rights and deployment behavior require task-specific review.

No OpenSpeech hardware benchmark yet; follow the checkpoint documentation.

Details reviewed 2026-09-20. Hardware figures are estimates unless a benchmark is linked.

Compare with similar

Compare all →

Choose an alternative to hear both models together.

No samples yet

Every model in this directory is read against the same three scripts so voices can be compared honestly — AuK-Flash’s samples just haven’t been generated yet.

Contribute samples on GitHub →

Run AuK-Flash

See the official repository installation guide.

AuK-Flash FAQ

Do I need a GPU to run AuK-Flash?

We have not verified a hardware requirement for this release. Follow the official setup instructions.

Can AuK-Flash clone voices?

Yes — AuK-Flash supports voice cloning from reference audio.

What license is AuK-Flash released under?

AuK-Flash is released under the MIT license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does AuK-Flash support?

AuK-Flash supports English, Chinese.

Is there a hosted AuK-Flash API?

OpenSpeech Cloud is accepting production-access interest for AuK-Flash, but this model is not currently hosted in Cloud. Use the official repository for current deployment options.