joeynyc / spark-voice
Voice assistant, voice studio and AI podcast that run entirely on NVIDIA DGX Spark. Pluggable models.
Why this job: says: voice assistant; topics: text-to-speech, speech-recognition, voice-cloning, voice-assistant
What it does
Three voice apps that run entirely on your own NVIDIA DGX Spark, with no cloud AI service:
Get started
git clone https://github.com/joeynyc/spark-voice && cd spark-voice
scripts/setup.sh
docker compose --profile app --profile models up -d - Maintenance
- Active
- Last commit 8 days ago
- Stars
- 10
- +1 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.1.0
- Released 8 days ago
- Built with
- HTML
- 60% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 0 merged
- 0 waiting
- Releases
- 1
- 1 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| AnubhavChaturvedi-GitHub / jarvis-ai-assistant | 393 | 2 months ago | GPL-3.0 | No downloads |
| PedroMarinhoDev / ComfyUI-Drama3 | 166 | 15 days ago | GPL-3.0 | No downloads |
More: languages, topics and project record
Languages
- HTML 60%
- Python 38%
- Dockerfile 1%
- Shell <1%
Topics
- ai-podcast
- dgx-spark
- docker-compose
- fastapi
- grace-blackwell
- local-ai
- ming-tts
- nemotron
- nvidia
- on-device-ai
- podcast-generator
- searxng
Project record
- JobSpeech and audio
- StatusNew to our list
- Commits2
- Forks1
- Watching0
- CreatedNov 1, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026