Lure 0.6B
Lure 0.6B is an English text-to-speech model that can clone a voice from a 3–12 second reference clip and its transcript. It supports streaming audio, inline sound tags, and optional free-text acting directions.
What it does
Use it to generate expressive English speech in a supplied voice, including specified sounds such as sighs or laughs.
- Availability
- Research preview; live demo and model weights are linked
- Pricing model
- Not established
- Deployment
- Local use with lure-tts; Mac, NVIDIA, and CPU options are documented
- Privacy
- Not established
- Licence
- Apache 2.0 for the weights, engine, and training code
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- Lure is a 0.6B text-to-speech model for English. [1]
Lure is a 0.6B text-to-speech model for English.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Voice cloning uses a 3 to 12 second reference and its transcript. [1]
- Inline sound tags can specify sounds at a chosen spot in the text. [1]
Write tags in round brackets, lowercase, at the spot where the sound should happen:
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model is described as a research preview, and weights are available to download.
- The lure-tts engine supports Mac, NVIDIA, and CPU options. [1]
### lure-tts (recommended: streaming, Turbo, Mac / NVIDIA / CPU)
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Lure supports English only. [1]
On the public English benchmarks below, Lure's word accuracy
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
Hugging FaceOwner-controlled
https://huggingface.co/Tesslate/Lure-TTS-0.6B
Retrieved 2026-10-29 00:21 UTC
Verified
Versions
2| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 2 | 2026-10-29 00:21 UTC | material change | access, deployment, pricing, availability, deployment | Current |
| 1 | 2026-10-27 00:11 UTC | publication | None | Current |
In briefs
1- Create expressive speech from a short voice sample Daily brief 2026-10-27
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.