Open-weight model
vani-indic-voice-assistant
by Saurabh Kumar thedevsaurabh/vani-indic-voice-assistant
vani-indic-voice-assistant is an open-weight model from Saurabh Kumar. Its published files total 349.6 KB.
Vani is a Cloud + Local Hybrid multilingual voice-to-voice assistant supporting all 22 Constitutionally Recognized Indian Languages using state-of-the-art speech and language models: 1.
Model Card
Vani is a Cloud + Local Hybrid multilingual voice-to-voice assistant supporting all 22 Constitutionally Recognized Indian Languages using state-of-the-art speech and language models: 1. Cloud / Browser WebRTC Mode (Hugging Face Spaces, Mobile, Any Browser): - Streams your microphone audio directly through the browser (gr.Audio(streaming=True)). - Evaluates speech boundaries in real time via LiveKit Silero ONNX VAD. - Auto-plays crystal-clear synthesized Indic speech in your browser with 3-Layer Acoustic Echo Protection so the assistant never hears itself. 2. Local Zero-Click Hardware Mode (Windows / Desktop GPU): - Captures audio directly from your OS soundcard via sounddevice.InputStream…
Excerpt from the card by Saurabh Kumar.
Identity and Version
- Repository
- thedevsaurabh/vani-indic-voice-assistant
- Publisher
- Saurabh Kumar
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- b89233073c1aad3a2b87b8c90e6d94a1b3ac21f3
- First published
- 2026-10-13
- Last updated
- 2026-10-13
Files and Weights
30 files, 349.6 KB in total.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| app.py | Configuration | 39.1 KB | — |
| config.py | Configuration | 4.2 KB | — |
| deploy_to_hf.py | Configuration | 3.7 KB | — |
| parler_tts/__init__.py | Configuration | 704 B | — |
| parler_tts/configuration_parler_tts.py | Configuration | 14.8 KB | — |
| parler_tts/dac_wrapper/__init__.py | Configuration | 78 B | — |
| parler_tts/dac_wrapper/configuration_dac.py | Configuration | 833 B | — |
| parler_tts/dac_wrapper/modeling_dac.py | Configuration | 6.2 KB | — |
| parler_tts/logits_processors.py | Configuration | 2.5 KB | — |
| parler_tts/modeling_parler_tts.py | Configuration | 190.6 KB | — |
| parler_tts/streamer.py | Configuration | 7.2 KB | — |
| src/__init__.py | Configuration | 45 B | — |
| src/asr_engine.py | Configuration | 3.9 KB | — |
| src/live_agent.py | Configuration | 19.0 KB | — |
| src/llm_engine.py | Configuration | 3.2 KB | — |
| src/pipeline.py | Configuration | 6.0 KB | — |
| src/tts_engine.py | Configuration | 8.1 KB | — |
| src/vad_engine.py | Configuration | 7.1 KB | — |
| test_barge_in_and_streaming.py | Configuration | 10.9 KB | — |
| test_env.py | Configuration | 2.4 KB | — |
| test_pipeline.py | Configuration | 1.3 KB | — |
| README.md | Documentation | 2.0 KB | — |
| test_report.md | Documentation | 3.9 KB | — |
| packages.txt | Other | 35 B | — |
| requirements.txt | Other | 256 B | — |
| run.bat | Other | 954 B | — |
| run_agent.bat | Other | 977 B | — |
| setup_env.ps1 | Other | 1.8 KB | — |
| .gitattributes | Repository | 7.9 KB | — |
| .gitignore | Repository | 63 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
Released by Saurabh Kumar through its official repository on Hugging Face.