rudrankriyam / Ichi
Experimenting with conversational AI in iOS, macOS and visionOS apps
Why this job: topics: tts, stt
What it does
- Privacy-First. All processing happens on-device - no data leaves your device
- Conversational AI. Powered by on-device LLMs (Qwen model)
- Speech Recognition. Real-time speech-to-text conversion
- Text-to-Speech. Natural voice synthesis using Kokoro TTS
- Apple Platform UI. SwiftUI app shell, currently validated on macOS while the MLX audio stack evolves
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 months ago
- Stars
- 112
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Swift
- 100% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 6 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| jianchang512 / pyvideotrans | 19,689 | today | GPL-3.0 | No downloads |
| GetStream / Vision-Agents | 8,202 | yesterday | Apache-2.0 | No downloads |
| gojargo / jargo | 109 | 5 days ago | BSD-2-Clause | Linux |
More: languages, topics and project record
Languages
- Swift 100%
Topics
- conversational-ai
- llm
- stt
- swift
- swiftui
- tts
Project record
- JobSpeech and audio
- StatusListed
- Commits72
- Forks5
- Watching3
- Stars in 28 days0
- CreatedNov 29, 2024
- First seen by usNov 7, 2026
- CheckedNov 7, 2026