All models
expressive

TADA 3B Multilingual

MIT (code) · Llama 3.2 Community License (weights)

Aligned text and speech generation with multilingual reference prompts.

Aligned text and speech generation with multilingual reference prompts. Requires the separate TADA codec and access to the Llama base model. Non-English reference audio should include a transcript.

Hear TADA 3B Multilingual

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

TADA 3B Multilingual · Default · Same three scripts across the directory.

Best for: Aligned text and speech generation with multilingual reference prompts.

Before you choose: Requires the separate TADA codec and access to the Llama base model. Non-English reference audio should include a transcript.

No comparable hardware benchmark verified. Check the official setup for your device.

Details reviewed 2026-09-14. 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 — TADA 3B Multilingual’s samples just haven’t been generated yet.

Contribute samples on GitHub →

Run TADA 3B Multilingual

pip install hume-tada
# Accept the Llama 3.2 access terms and follow the TADA inference example.

TADA 3B Multilingual FAQ

Do I need a GPU to run TADA 3B Multilingual?

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

Can TADA 3B Multilingual clone voices?

Yes — TADA 3B Multilingual supports voice cloning from reference audio.

What license is TADA 3B Multilingual released under?

TADA 3B Multilingual is released under the MIT (code) · Llama 3.2 Community License (weights) license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does TADA 3B Multilingual support?

TADA 3B Multilingual supports English, Arabic, Chinese, German, Spanish, French, Italian, Japanese, Polish, Portuguese.

Is there a hosted TADA 3B Multilingual API?

OpenSpeech Cloud is accepting production-access interest for TADA 3B Multilingual, but this model is not hosted in the beta. Use the official repository for current deployment options.