# Hume AI releases TADA-1B, an English TTS that aligns one speech vector per text token

> TADA-1B is Hume AI's open English TTS built on Llama 3.2 1B, with 1:1 text-to-speech alignment; Llama 3.2 licence.

Published 2026-01-12

Canonical: https://shipped.anth.us/open-weights/humeai-tada-1b/

Hume AI published TADA-1B, an English text-to-speech model built on Llama 3.2 1B. The Hub lists it at 2B parameters in BF16, though the name says 1B. The card describes 1:1 alignment, where the tokenizer produces one speech vector per text token, which it says removes the need for fixed-frame-rate processing, and dual-stream generation that produces a text token and the preceding token's speech together. Speech continuation is supported through a num_extra_steps setting.

The Evaluation section shows four charts (CER, real-time speed, speaker similarity, MOS naturalness) but the page text gives no numbers, so none are repeated here. The card mentions a separate TADA-3B-ml model sharing the same encoder. No Inference Provider hosts it, and the example code assumes a CUDA device.

The licence is tagged llama3.2, and the card says the project is built with Llama 3.2 under the Llama 3.2 Community License. The card gives no release date; the date used is the Hugging Face repo creation date, and the linked paper is listed as published 26 February.

An interesting architecture with its results in pictures.

## Sources
- [Hume AI model card on Hugging Face](https://huggingface.co/HumeAI/tada-1b)
- [Hugging Face repo metadata (creation date)](https://huggingface.co/api/models/HumeAI/tada-1b)

## Editor's first pass (AI-assisted)
- Real 3.5: Weights are public but you must run it yourself, from GitHub, on CUDA.
- Useful 3: English only, with no numeric results in the card text.
- Notable 3: A known voice-AI company opening a model.
- Novel 4: One speech vector per text token with dynamic duration is a distinct design.