dograh (dograh-hq/dograh) is an open-source AI project on GitHub. Repository summary: Open Source Voice Agent Platform Its focus includes speech and audio processing. It is suitable for extension, integration, and iterative delivery in real workflows.
License
BSD-2-Clause
Stars
1,120
Homepage
https://app.dograh.com/Features
- Core capability: Open Source Voice Agent Platform
- Supports speech recognition, synthesis, or audio processing
- Repository: dograh-hq/dograh
- Primary language: Python
- Open-source license: BSD-2-Clause
- GitHub traction: about 1,104 stars
Use Cases
- Used for meeting transcription, voice assistants, and audio production
- Build internal AI workflow prototypes with dograh
- Validate dograh in production-like engineering scenarios
- Customer support and Q&A assistants
- Virtual character and companion scenarios
- Automating conversational team workflows
FAQ
Teams should first define integration boundaries and call patterns, then map repository capabilities into concrete interfaces, parameters, and access rules. GitHub repository: https://github.com/dograh-hq/dograh. Community traction is around 1,104 stars. License: BSD-2-Clause.
It usually works as an execution component or capability layer, with common deployment fits such as: Used for meeting transcription, voice assistants, and audio production, Build internal AI workflow prototypes with dograh, Validate dograh in production-like engineering scenarios.
