Hume AI

The empathic AI research lab. Providing the open source models, datasets, and evaluation APIs to embed emotional intelligence into your models.

[Hume AI @hume_ai]

Today we're releasing our first open source TTS model, TADA!

TADA (Text Audio Dual Alignment) is a speech-language model that generates text and audio in one synchronized stream to reduce token-level hallucinations and improve latency.

This means:
→ Zero content hallucinations across 1,000+ test samples

→ 5x faster than similar-grade LLM-based TTS

→ Fits much longer audio: 2,048 tokens cover ~700 seconds with TADA vs. ~70 seconds in conventional systems

→ Free transcript alongside audio with no added latency

[Hume AI @hume_ai]

https://t.co/Fy0OZYrUtX

[Hume AI @hume_ai]

Today, voice models have no problem generating “angry” or “sad” expressions.

But ask for:
→ bored + fast
→ joy + shy
→ disappointment + confident
…and most systems collapse into stereotypes.

Our latest research blog explores why this happens — and how disentangling emotion from voice at the data layer improves expressive control. Read more below!

[Hume AI @hume_ai]

@derek1159 We are too!

[Hume AI @hume_ai]

We’re excited to launch the 2026 ACII Dyadic Contest (DaiKon) Workshop & Challenge—a new benchmark for modeling emotional influence in dyadic dialogue.

Explore a sample of our conversational audio dataset: 945 sessions, 743 hours, across 5 languages.

Submissions due May 25. We look forward to your participation!

[Hume AI @hume_ai]

This dataset at scale is also available in its original dual-channel format. Explore more of our training datasets at https://t.co/C5p5lAtDYl

[Hume AI @hume_ai]

Register and find out more at
https://t.co/DyEf9ereL1

[Hume AI @hume_ai]

Find more here 👇
https://t.co/RBhWViOHhW
https://t.co/PQGfrpfQhY

[Hume AI @hume_ai]

Today, we're shipping MLX support for TADA, our open-source text-to-speech model, which means the entire pipeline (LLM, flow-matching, and decoder) can now run locally on any Apple Silicon device. We're seeing a 45% reduction in memory usage and a 10x speed-up when using it quantized. With these improvements, you can use TADA on-device for OpenClaw or any personal chatbot.

If you own a MacBook, Mac Mini, or Mac Studio, record a 10-second clip of any voice, type any text, and get high-quality, natural and expressive speech in real-time. Completely offline, completely free.

[Hume AI @hume_ai]

@fffiloni @huggingface @Gradio Great work!

[Sylvain Filoni @fffiloni]

I made a @huggingface Space @Gradio demo for TADA to make the paper’s workflow easier to explore.

The original demo was a bit confusing, so this one is more guided and helps you understand what’s really going on — and in what order the pipeline is supposed to work.

[Hume AI @hume_ai]

@wuzhu_ @huggingface @grok It is not fine-tuned for languages outside of English, though it has some multilingual capabilities!

[Hume AI @hume_ai]

Today we're releasing our first open source TTS model, TADA!

TADA (Text Audio Dual Alignment) is a speech-language model that generates text and audio in one synchronized stream to reduce token-level hallucinations and improve latency.

This means:
→ Zero content hallucinations across 1,000+ test samples

→ 5x faster than similar-grade LLM-based TTS

→ Fits much longer audio: 2,048 tokens cover ~700 seconds with TADA vs. ~70 seconds in conventional systems

→ Free transcript alongside audio with no added latency

[Hume AI @hume_ai]

@CastrikoEdit It is not fine-tuned for languages outside of English, though it has some multilingual capabilities!

[Hume AI @hume_ai]

@overbeight Please try again and let us know if you're still seeing this!

[Hume AI @hume_ai]

@_NeutralFan_ It is not fine-tuned for languages outside of English, though it has some multilingual capabilities!

[Hume AI @hume_ai]

@rajbreno It is not fine-tuned for languages outside of English, though it has some capabilities in other languages.

[Hume AI @hume_ai]

@brubbleR Try again and let us know if you're running into issues!

[Hume AI @hume_ai]

@0xecall Please try again and let us know if you're still running into this issue!

[Hume AI @hume_ai]

Read our blog: https://t.co/KqNp4jD0lV

[Hume AI @hume_ai]

Try the model: https://t.co/kY2sSifaXq