Voice: speakers and sound

Smart Turn

Uses intonation to tell whether a person has finished a thought or just paused, so a voice bot does not interrupt. Version 3 is 8 MB, runs on a CPU and understands 23 languages, including Russian.

Developer
Daily (Pipecat), USA
First release
Mar 2025
Latest release
Jan 2026
Sizes
8M (v3) – 580M (v1)
License
Commercial use allowedBSD 2-Clause
Russian
Supported
Running
On your own serverAlso runs without a GPU
Industries
Customer support, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Voice bot does not interrupt the customer during pauses
  • Fast reply when the customer has really finished
  • An add-on to a standard speech detector in voice assistants

Where it is used

Call centersVoice bots and assistantsAppointment booking and delivery

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. v3.2
  2. v3.1
  3. v3 (8M, работает на процессоре)
  4. v2
  5. Smart Turn v1

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Smart Turn be used in a commercial project?

Yes. License: BSD 2-Clause. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Smart Turn need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Smart Turn support Russian?

Yes, Russian is listed on the model card.

Where can I download Smart Turn and what does it cost?

The Smart Turn weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Voice: speakers and soundSilero VADSilero · RussiaCommercial use allowed

The most popular open speech detector: tells voice apart from silence and noise. Processes an audio chunk in under a millisecond on a single CPU core; trained on recordings in more than 6,000 languages.

DetailsVoice: speakers and soundTEN VADAgora (TEN project) · USA / ChinaCommercial use with conditions

A lightweight speech detector for real-time voice assistants: it notices the start and end of a phrase faster than Silero VAD. Runs on servers, phones and in the browser.

DetailsVoice assistantsMoshi / HibikiKyutai · FranceCommercial use with conditions

A voice assistant that listens and speaks at the same time, with no delay for recognition and synthesis. Hibiki does simultaneous speech-to-speech translation between several European languages.

Details

Source: huggingface.co/api/models/pipecat-ai/smart-turn-v3/commits/main. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.