# WhisperSage — Private Local AI Assistant

> Private Local AI Assistant (iPhone/iPad app by 智慧 焦.)

- Source: https://appshunter.io/ios/app/whispersage/id6477900227 (this page in markdown: same URL + `.md`)
- Developer: [智慧 焦](https://appshunter.io/developer/1722375071)
- Category: Lifestyle, Productivity
- Price: $1.99
- Age rating: 17+
- Requires: iOS 17.0 · 2.0 GB
- Languages: English, Chinese
- Released: 2024-04-01
- Data updated: 2026-06-04
- User reviews in markdown: https://appshunter.io/ios/app/whispersage/id6477900227/reviews.md

## What is WhisperSage?

Welcome to WhisperSage, your personal private local AI chat assistant.

Core Features:
- Conversation Management: Easily create, manage, and delete conversations.
- Privacy Protection: No need to connect to the internet, all conversations are stored locally, ensuring your information is secure and private, allowing you to use it with confidence.
- Model Management: Download models from Huggingface.co or use a remote model with ollama(https://ollama.com/, make sure ollama binds to 0.0.0.0 not localhost, and firewall is closed). Support both text model and multimodal model.
- Simple and Easy to Use: A user-friendly interface design makes managing conversations an easy and enjoyable task. Support speech input(speech to text, STT) with OpenAI Whisper local model.

IMPORTANT NOTE: Make sure you have enough memory to run the model, at least 1.5 times the size of the model (an additional 300MB for speech input and an additional 1.5GB for multimodal model). Considering user experience, the app is intend to run properly on iPhone 14 or newer devices, or devices with Apple Silicon M-series chips.

If you have any questions, please leave a message or send me an email.
Email：jzhihui521@gmail.com


## Version history (last 5 releases)

### 1.2.2 — 2024-06-08

- Update default model to Qwen2-1.5B-Instruct-Q4.
- Support download latest Qwen2 model: Qwen2-7B-Instruct-Q4.
- Fix potential bug.

### 1.2.1 — 2024-05-07

- Support download latest models: Llama-3-8B-Instruct-Q4 and Phi-3-mini-4k-instruct-Q4.
- Support multimodal model: moondream2.
- Support speech input(speech to text, STT) with OpenAI Whisper local model.
- Make the default context length to 1024.
- Fix bug for default chat name.

### 1.2.0 — 2024-05-05

- Support download latest models: Llama-3-8B-Instruct-Q4 and Phi-3-mini-4k-instruct-Q4.
- Support multimodal model: moondream2.
- Support speech input(speech to text, STT) with OpenAI Whisper local model.
- Make the default context length to 1024.

### 1.1.0 — 2024-04-03

1. Support download models from Huggingface.co, include Qwen1.5-4B-Chat-Q4, Qwen1.5-7B-Chat-Q4, Mistral-7B-Instruct-v0.2-Q4, phi-2-Q4, gemma-2b-it-Q4, gemma-7b-it-Q4.
2. Support setting a remote model info include model name and model URL with ollama(https://ollama.com/, make sure ollama binds to 0.0.0.0 not localhost, and firewall is closed).
3. You can switch the model when chatting with your assistant.
4. The default context length is 512.
5. Support sample with repetition penalties when generate tokens.

### 1.0.0 — 2024-03-25

No release notes.

## Apps similar to WhisperSage

| App | Rating | Price | Category |
| --- | --- | --- | --- |
| [ai journal,my diary: DiaryAI](https://appshunter.io/ios/app/ai-journalmy-diary-diaryai/id6477748437) | 3.5 (2) | Free | Lifestyle |
| [MyProxi](https://appshunter.io/ios/app/myproxi/id6470256241) | 5.0 (2) | Free | Lifestyle |
| [Flirtify AI](https://appshunter.io/ios/app/flirtify-ai/id6449322624) | 4.2 (20) | Free | Lifestyle |
| [Sauce: Speak Confidently](https://appshunter.io/ios/app/sauce-speak-confidently/id6742469449) | 4.6 (170) | Free | Lifestyle |
| [Evai](https://appshunter.io/ios/app/evai/id6477519145) | 4.7 (13) | Free | Lifestyle |
| [Vurbs](https://appshunter.io/ios/app/vurbs/id6717610689) | 4.5 (8) | Free | Lifestyle |

---

*Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-06-04.*