Volocal

Name: Volocal
Rating: 4 (2 reviews)
Author: Fikri Karim

By: Fikri Karim App

Voice AI, Fully On-Device

Overview

Version:

1.0.0

Last updated: 2026-04-02

Ranking

#819,525 ▼ 10,462

Overall

Features & Capabilities

Talk to an AI voice assistant that runs 100% on your iPhone. No cloud, no subscriptions, no internet needed. Your conversations never leave your device.

Talk to an AI assistant that runs entirely on your iPhone. No cloud servers, no API keys, no subscriptions -- just real-time voice conversations powered by on-device intelligence.

FULLY PRIVATE, FULLY LOCAL

Every word you say stays on your device. Volocal runs three specialized AI models directly on your iPhone's hardware -- nothing is ever sent to the internet. After downloading the models on first launch, you never need a network connection again.

REAL-TIME VOICE CONVERSATIONS

Speak naturally and hear responses streamed back in real-time. Volocal uses a three-stage pipeline -- Speech-to-Text, Language Model, and Text-to-Speech -- all running simultaneously on different chips inside your phone for smooth, low-latency conversations.

INTERRUPT ANYTIME

Change your mind mid-sentence? Just start talking. Volocal supports barge-in with hardware echo cancellation, so the microphone stays active even while the assistant is speaking. No need to wait for it to finish.

NO SUBSCRIPTIONS, NO API KEYS

Volocal is completely free and open source. There are no in-app purchases, no subscriptions, and no hidden costs. Download the models once (~2.3 GB, Wi-Fi recommended) and you're set.

HOW IT WORKS

Volocal splits the workload across your iPhone's specialized processors:

Speech recognition (Parakeet EOU) runs on the Neural Engine
Language model (Qwen3.5-2B) runs on the GPU via Metal
Text-to-speech (PocketTTS) runs on the Neural Engine

This separation means all three models can run at the same time without competing for resources, keeping conversations fluid and responsive.

LIGHTWEIGHT

Total runtime memory usage is approximately 1.2 GB, well within the limits of modern iPhones.

REQUIREMENTS

iOS 17 or later
Physical device only (Neural Engine is not available in the Simulator)
~2.3 GB of storage for model downloads on first launch

Volocal is MIT licensed and open source. Built by Fikri Karim.

User Growth & Download Statistics

App

By:

Fikri Karim

Rating:

4.00

(2)

Version:

1.0.0 Last updated: 2026-04-02

Version code:

884030435

Creation date:

2026-04-02

Compatible devices:

Size:

12.66MB

URLs:

Website ,Privacy policy

Full description:

Source:

Apple Apps Store

Data ingested on:

2026-07-16

Compare stats and ranking:

Ranking

# 819,525 ▼ 10,462

For Developers

Monetize with App Pass Boost with Extension Booster

Contact the developer

Chrome-Stats does not own this Apple app. Please use these information below to contact the Apple app developer.

Developed by:

Fikri Karim

Apple Apps Store

https://apps.apple.com/us/app/volocal/id6761493288

Website:

https://github.com/fikrikarim/volocal

User Reviews

This app seriously needs some md5 checksums for the downloaded models. Often times the connection glitched out(no idea, the LLM and the text to speech model have high probability to fail), the model became partially downloaded, and this app thinks it is fully downloaded then proceed to tell me "error loading the GGUF model". There is no re-downloading, I have to delete the whole app and start all over again. A slight error for any of these 3 models would cause me to delete and reinstall again and again. I even hope it can use a local LAN hosted LLM for a complete workaround for such downloading issue.