n0an / VivaDicta
iOS & watchOS speech-to-text app with AI voice keyboard, on-device RAG, and chat with your notes - powered by Apple Foundation Models, WhisperKit, NVIDIA Parakeet, and 20+ AI providers
Why this job: says: speech to text; topics: asr, speech-to-text
What it does
- On-device. WhisperKit (OpenAI Whisper), Parakeet (NVIDIA) - professional-grade models running entirely on your device
- Cloud. OpenAI, Groq, Cohere, Deepgram, ElevenLabs, Gemini, Mistral, Soniox, or any OpenAI-compatible endpoint
- 100+ languages with automatic detection
- Diarization. speaker-separated transcripts for meetings, interviews, and group conversations
- Filler word removal, paragraph formatting, custom word replacements
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 days ago
- Stars
- 141
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v3.13.0
- Released 2 days ago
- Built with
- Swift
- 92% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- 77% closed
- 5 still open
- Pull requests
- 363 merged
- 1 waiting
- Releases
- 27
- 27 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| k2-fsa / sherpa-onnx | 15,840 | 2 days ago | Apache-2.0 | Mac, Linux |
| rudrankriyam / Foundation-Models-Framework-Lab | 1,191 | 2 days ago | MIT | No downloads |
| argmaxinc / argmax-oss-swift | 6,447 | 29 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Swift 92%
- Python 7%
- Shell 1%
- Metal <1%
Topics
- asr
- foundation-models
- ios
- rag
- speech-to-text
- watchos
Project record
- JobSpeech and audio
- StatusListed
- Commits3,407
- Forks19
- Watching0
- Stars in 28 days+10
- CreatedAug 2, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026