dwani.ai is a self-hosted, multimodal inference system designed for Indian Languages.
Interact using Text, Voice, Image and Documents for learning, analysis and exploration.
pip install --upgrade dwani
import dwani
import os
dwani.api_key = os.getenv("DWANI_API_KEY")
dwani.api_base = os.getenv("DWANI_API_BASE_URL")
- gemma3 - with translation
resp = dwani.Chat.create(prompt="Hello!", src_lang="english", tgt_lang="kannada", model="gemma3")
print(resp)
{'response': 'ನಮಸ್ತೆ! ಭಾರತ ಮತ್ತು ಕರ್ನಾಟಕವನ್ನು ಗಮನದಲ್ಲಿಟ್ಟುಕೊಂಡು ಇಂದು ನಿಮ್ಮ ಪ್ರಶ್ನೆಗಳಿಗೆ ನಾನು ನಿಮಗೆ ಹೇಗೆ ಸಹಾಯ ಮಾಡಲಿ?'}
Website -> dwani.ai
Chat UI -> chat.dwani.ai
Workshop PPT -> workshop-ppt
- Measure and improve the Time to First Token Generation (TTFTG) for model architectures in ASR, Translation, and TTS systems.
- Develop and enhance a Kannada voice + OCR model that meets industry standards set by OpenAI, Google, ElevenLabs, xAI
- Create robust voice solutions for Indian languages, with a specific emphasis on Kannada.
The project utilizes the following open-source tools:
Open-Source Tool | Source Repository |
---|---|
Automatic Speech Recognition : ASR | ASR Indic Server |
Text to Speech : TTS | TTS Indic Server |
Translation | Indic Translate Server |
Document Parser | Indic Document Server |
dwani API Server | Dwani Server |
dwani Android | Android |
dwani python sdk | python-sdk |
vllm-arm64 | vllm-arm64 |
Feature | Description | Components |
---|---|---|
Voice AI | Provides answers to voice queries using a LLM | ASR + LLM |
Text Translate | Translates text from one language to another. | Translation |
Text Query | Allows querying text data for specific information. | LLM |
Voice to Text Translation | Converts spoken language to text and translates it. | ASR, Translation |
PDF Translate | Translates content from PDF documents. | |
Text to Speech | Generates speech from text. | TTS |
Voice to Voice Translation | Converts spoken language to text, translates it, and then generates speech. | ASR, Translation, TTS |
Answer Engine with Translate | Provides answers to queries with translation capabilities. | ASR, LLM, Translation, TTS |
- For any questions or issues, please open an issue on GitHub or contact us via email.
- For collaborations
- Join the discord group - invite link
- For business queries, Email : sachin (at) dwani (dot) ai