---
title: oruk
emoji: 🌊
colorFrom: blue
colorTo: purple
sdk: static
pinned: false
short_description: humanizing speech AI
---

<a href="https://oruk.ai"><img src="https://huggingface.co/spaces/oruk/README/resolve/main/assets/oruk-header.png" alt="oruk — humanizing speech AI" width="1212" /></a>

We train speech models to help AI understand what people say, how they say it, and what they mean—directly from the audio.

[Try the demo](https://demo.oruk.ai) · [Explore our models](https://oruk.ai/models) · [API docs](https://oruk.ai/docs) · [Research](https://oruk.ai/research)

### Speech understanding, from the audio

**Words and speakers.** Transcribe speech and follow who said what, with time-coded segments.  
**Emotion and delivery.** Add context from tone, rhythm, emphasis, and vocal expression.  
**One API.** Bring transcripts and acoustic context into the products you build.

### Open research

- **[Orukeet](https://huggingface.co/oruk/orukeet)** — our open multilingual speech recognition model, with code, weights, evaluation results, and a technical report.
- **[oruk-bench](https://huggingface.co/datasets/oruk/oruk-bench-leaderboard)** — published speech-emotion evaluation results, with methods and limitations documented alongside the scores.
- **[Research highlights](https://oruk.ai/research)** — experiments, model releases, and interactive explanations from the team.

Built by researchers from Stanford, Berkeley, and Cambridge. [Meet the team →](https://oruk.ai/company)

[Website](https://oruk.ai) · [GitHub](https://github.com/Oruk-AI) · [Brand assets](https://oruk.ai/branding) · [Contact](mailto:access@oruk.ai)