kenpath/svara-tts-v1
text-to-speech model by kenpath
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
[](https://huggingface.co/kenpath/svara-tts-v1) [](https://huggingface.co/spaces/kenpath/svara-tts) [](https://colab.research.google.com/drive/15YxFo1DzdQNbFUIZ1HJA4AN4oHqKxGtg) [](https://github.com/Kenpath/svara-tts-inference) svara-TTS is a developer-first multilingual TTS model for 19 languages (18 Indic + Indian English). Built on an Orpheus-style discrete audio token approach, it targets clarity, expressiveness, and low-latency on commodity GPUs/CPUs. It supports light-weight emotion/style control (e.g., , , , ) and simple speaker identities (Language (Gender)), with zero-shot adaptation paths. Try it live on the Demo Space, or on Colab Deployment scripts and inference repo will be available soon. Watch our Github for updates आज... सच में अच्छी खबर है — शाम को मिलते हैं! Trained on 2000+ hours of open, high-quality speech from SYSPIN, RASA, IndicTTS, and SPICOR, covering 50 speakers (balanced male/female) across 19 languages. Data was curated to encourage…
Read the full model card ↗ · Preview checked 2026-10-28T09:55:58.088Z
Inside the original model card — Document outline
- svara-TTS v1 — Open Multilingual TTS for India’s Voices
- At a Glance
- Prompting (Orpheus-style)
- Training Data Summary
- Intended Uses
- Out-of-Scope / Not Intended
- Limitations
- Responsible Use
- Sources & Links
- 🙏 Acknowledgments
- License
- Versioning & Changelog
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
kenpath/svara-tts-v1 is a text-to-speech model repository published by kenpath on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-speech
- Library
- transformers
- Recent downloads (30 days)
- 105,035
- Cumulative likes
- 64
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 3,300,867,072
- Architecture
- LlamaForCausalLM
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2025-10-26T15:23:57.000Z
- Last modified
- 2025-10-27T17:39:55.000Z
Compatibility and lineage
Reported languages: hi, bn, mr, te, kn, bho, mag, hne, mai, as, brx, doi, gu, ml, pa, ta, ne, sa, en
Reported base models: canopylabs/3b-hi-ft-research_release
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:52:33.137Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.