README / README.md
MeetJariwala100's picture
Add ZeroRuntime organization card
b0b19e7 verified
|
Raw
History Blame Contribute Delete
4.47 kB
---
title: README
emoji: 🎙️
colorFrom: blue
colorTo: gray
sdk: static
pinned: false
---
![ZeroRuntime. Voice AI Agents for Every Developer.](assets/banner.png)
<div align="center">
### Real-time voice AI infrastructure, and the models that make it fast.
<a href="https://zeroruntime.ai/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface"><img src="https://img.shields.io/badge/Start%20building-zeroruntime.ai-AAC7FF?style=for-the-badge&labelColor=181818" alt="Start building"></a>
&nbsp;
<a href="https://docs.zeroruntime.ai/introduction?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface"><img src="https://img.shields.io/badge/Docs-Read%20the%20guide-285290?style=for-the-badge&labelColor=181818" alt="Docs"></a>
&nbsp;
<a href="https://community.zeroruntime.ai/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface"><img src="https://img.shields.io/badge/Community-Join-285290?style=for-the-badge&labelColor=181818" alt="Community"></a>
</div>
This is ZeroRuntime's home on Hugging Face for the models we build in house and the research behind them. Everything here is designed to give developers and researchers production-grade starting points for real-time voice, backed by the same work that powers the ZeroRuntime platform.
---
## What is ZeroRuntime?
An AI voice agent infrastructure platform for building, deploying and running production voice AI agents across **web, mobile, telephony and physical devices**.
- **One optimized system.** Transport layer, agent logic and voice components together, so orchestration overhead and latency both drop.
- **Agents start on demand.** No pre-reserving, so concurrent sessions scale without you managing the infrastructure.
- **Your stack, your choice.** Bring your own LLM, STT and TTS.
![One optimized runtime brings speech, models and real-time audio together. Up to 70% lower latency.](assets/runtime.png)
| | |
|---|---|
| **Runtime** | Speech, models and audio in one system. Up to **70% lower latency** |
| **SDKs** | Voice agents for web, mobile, telephony and devices |
| **Cloud** | Managed infrastructure, agents start on demand |
| **Playground** | Test live, switch models, inspect latency, tune prompts |
---
## Research
We build proprietary models when off-the-shelf solutions fall short on speed or accuracy.
![Know when to respond. Echo turn detection, benchmarked against the field.](assets/research.png)
### Echo: turn detection
Knowing when a person has actually finished talking is the difference between a conversation and an interruption. Silence timers guess. Echo does not.
| Model | Reads | Built for |
|---|---|---|
| **Echo Small** | Transcript | The lowest latency |
| **Echo Large** | Transcript | Higher accuracy |
| **Echo Omni** | **Audio + transcript** | Multimodal accuracy across **27 languages** |
- Up to **97.3% completed-turn recall** at over **93% overall accuracy**
- Four states, not two: **Complete**, **Incomplete**, **Backchannel**, **Wait**
- Trained on data we build in house, for a problem public corpora do not cover
---
## Enterprise
- Encryption, audit trails and certifications that clear security and procurement
- Your data stays yours. No third party touches a call
---
<div align="center">
### Your next voice AI experience starts here.
<a href="https://zeroruntime.ai/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface"><img src="https://img.shields.io/badge/Get%20started%20free-zeroruntime.ai-AAC7FF?style=for-the-badge&labelColor=181818" alt="Get started free"></a>
&nbsp;
<a href="https://zeroruntime.ai/talk-to-expert?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface"><img src="https://img.shields.io/badge/Talk%20to%20an%20expert-285290?style=for-the-badge&labelColor=181818" alt="Talk to an expert"></a>
<sub>
[Docs](https://docs.zeroruntime.ai/introduction?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface) · [Code samples](https://github.com/ZeroRuntimeAI/zrt-python-sdk-examples) · [Pricing](https://zeroruntime.ai/pricing?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface) · [Blog](https://zeroruntime.ai/blog?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface) · [Community](https://community.zeroruntime.ai/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface)
</sub>
![ZERO_RUNTIME](assets/wordmark.png)
<sub>San Francisco · Surat</sub>
</div>