How much does Llasa 1B cost?

Llasa 1B is open source and can be self-hosted.

What benchmarks has Llasa 1B been tested on?

Llasa 1B has not been benchmarked yet. Scores are added as benchmarks are published.

How does Llasa 1B compare to GPT-5.4 Image 2?

Llasa 1B has an average score of 0.0 while GPT-5.4 Image 2 scores 0.0. GPT-5.4 Image 2 slightly outperforms Llasa 1B overall. See full comparison →

Home/Models/Llasa 1B

Llasa 1B

Name: Llasa 1B
Author: HKUST Audio

by HKUST Audio · Released Jan 2025

Open Source

Compare

Context

N/A

Input $/1M

TBD

Output $/1M

TBD

Type

text-to-speech

License

Open Source

Benchmarks

0 tested

Data updated today

About

HKUSTAudio text to speech model. 10K downloads on HuggingFace.

No benchmark data available yet.

Similar Models

GPT-5.4 Image 2

OpenAI

0.0$8.00/1M

Mistral Small 3.2 24B

Links

Info

Research

Documentation

Community

Source Code

BenchGecko API

hkustaudio-llasa-1b

Specifications

Typetext-to-speech
ContextN/A
ReleasedJan 2025
LicenseOpen Source
StatusActive

Available On

HKUST AudioTBD

Learn More

transformer open-weights tokens

Share & Export

Related Models

GPT-5.4 Image 2

0.0

Mistral Small 3.2 24B

0.0

Qwen VL Max

0.0

Elephant

0.0

Frequently Asked Questions

Llasa 1B is an open-source text-to-speech AI model by HKUST Audio, released in January 2025.

Benchmarks

HKUST Audio · Provider All Models Compare Models

Llasa 1B

Frequently Asked Questions

Related Models

Benchmarks

Related Pages