# Hlas

> A 3.5B-parameter expressive text-to-speech model with zero-shot voice cloning and inline performance tags across many languages.

Hlas (Czech for "voice") is an expressive text-to-speech model published on Hugging Face by cekal, fine-tuned from BreezeBlue's Breeze TTS 2. It has 3.5B parameters, clones voices zero-shot from a short reference clip, and takes performance direction through inline tags written in square brackets. The model is released under a BreezeBlue research and non-commercial license, while its inference runtime is Apache-2.0.

## What It Is

Hlas is a text-to-speech checkpoint that turns text into 24 kHz mono speech. The text carries both the words and the performance: emotions, deliveries, pauses, laughs, sighs, accents and characters are written in square brackets at the position where they should happen. The model card says it runs on a single 12 GB GPU and covers English, Mandarin and a broad set of further languages.

## How Tags and Cloning Work

Tags apply from the position where they appear, can be combined, and can be free-form short descriptions. Documented families include emotion, delivery, vocalization, pacing, character and accent, and free-form directions. Tags are written in English in every language. Punctuation also shapes delivery: ellipses hesitate, capitals stress, and exclamation marks add energy.

For voice cloning, the user supplies 3 to 15 seconds of clean reference speech plus its exact transcript. The output keeps the reference voice's timbre, accent and age, and tags still apply. Without a reference, a voice can be described in text through an instruction option.

## Running It

The checkpoint loads unchanged in the official Breeze TTS 2 runtime. The runtime provides a single-file inference script and a streaming server with an OpenAI-style speech endpoint that returns mono 24 kHz signed 16-bit PCM. A 12 GB GPU runs eager mode, and a 24 GB GPU can use the fast path. A live browser demo is linked from the model card.

## Features
- 3.5B-parameter expressive text-to-speech model
- Inline performance tags for emotions, deliveries, pauses and vocalizations
- Free-form tag directions
- Zero-shot voice cloning from a 3 to 15 second reference clip
- Voice description via text instruction without a reference
- Multilingual output including English, Mandarin, Spanish, French, German, Japanese and more
- 24 kHz mono output
- Streaming server with OpenAI-style speech endpoint
- Runs on a single 12 GB GPU

## Integrations
Breeze TTS 2 runtime, Hugging Face Hub, Safetensors

## Platforms
WEB, API, VSC_EXTENSION, CLI

## Pricing
Free

## Links
- Website: https://huggingface.co/cekal/hlas-1
- Repository: https://github.com/breezeblue-ai/breeze-tts
- EveryDev.ai: https://www.everydev.ai/tools/hlas