svara-tts-voiceclone-beta

[](https://huggingface.co/kenpath/svara-tts-voiceclone-beta) [](https://huggingface.co/spaces/kenpath/svara-tts) [](https://colab.research.google.com/) [](https://github.com/Kenpath/svara-tts-inference) **svara-tts-voiceclone-beta** is an experimental extension of **svara-tts-v1**, designed to bring **lightweight voice cloning** and improved **accent preservation** to Indic languages. It introduces a simple but effective **reference-swap finetuning** technique, enabling more stable zero-shot speaker identity across long, expressive utterances. Built on an Orpheus-style discrete audio token architecture, the model supports **19 languages**, expressive cues (`<laugh>`, `<yawn>`, `<angry>`), and low-latency TTS on commodity hardware. * **Languages (19):** Hindi, Bengali, Marathi, Telugu, Kannada, Bhojpuri, Magahi, Chhattisgarhi, Maithili, Assamese, Bodo, Dogri, Gujarati, Malayalam, Punjabi, Tamil, Nepali, Sanskrit, Indian English. * **Voice Cloning:** Improved consistency using **reference-swap finetuning**, works with short (≈10s) reference audio. * **Expressivity:** Emotion tags; non-verbal cues; improved Indic prosody. * **Low-Latency Deployment:** Fully compatible with GGUF and **vLLM**. * **Adaptability:** LoRA-ready; easy to specialize for speakers, domains, or dialects. Demo playback uses the same Space as svara-tts-v1. * Place style/emotion tags at the end: `आज शाम को जल्दी मिलते हैं। <neutral>` * Provide reference audio tokens before the target text. * Use punctuation to control rhythm, pauses, and emphasis. **Zero-shot example:** कल शाम को जल्दी मिलते हैं। <neutral> Speaker IDs remain compatible with svara-tts-v1: **`Language (Gender)`**. `svara-tts-voiceclone-beta` is enhanced from the multilingual base of **svara-tts-v1**, trained on: * **SYSPIN**, **RASA**, **IndicTTS**, **SPICOR** * ~2000 hours, ~50 speakers, balanced male/female * Rich phoneme coverage across 19 Indic languages The **reference-swap augmentation** uses multi-utterance samples to improve speaker consistency across Indic phonetic variation. * Zero-shot voice cloning for Indic voices * Dialogue systems, IVR, learning apps, accessibility solutions * Content creation, localization, storytelling * Research on speech identity, expressivity, and multilingual TTS * Impersonating private individuals without consent * Fraud, targeted deception, harassment * High-risk or safety-critical deployments * Perfect 1:1 replication of voices (this is a beta research release) * Zero-shot cloning is **not** identical to dedicated finetuning * Speaker similarity may degrade over long utterances * Varies by language due to dataset imbalance * Emotion emphasis may differ across low-resource languages * Rare names and numbers may require normalization or rewriting These improve with targeted LoRA finetuning or higher-quality data. By using this model, you agree to follow applicable laws and ethical guidelines. Synthetic speech should be disclosed when appropriate. Avoid impersonation or harmful use cases. * **Base Model (svara-tts-v1):** [https://huggingface.co/kenpath/svara-tts-v1](https://huggingface.co/kenpath/svara-tts-v1) * **Demo Space:** [https://huggingface.co/spaces/kenpath/svara-tts](https://huggingface.co/spaces/kenpath/svara-tts) * **Inference Repo:** [https://github.com/Kenpath/svara-tts-inference](https://github.com/Kenpath/svara-tts-inference) * **Indic Text Normalizer:** [https://github.com/Kenpath/indic-text-normalization](https://github.com/Kenpath/indic-text-normalization) Developed by **Kenpath Technologies**. Special thanks to: * **Canopy Labs — Orpheus** (architecture & research release) * **SYSPIN / SPICOR — IISc Bangalore** * **AI4Bharat — RASA** * **IIT Madras — IndicTTS** * **Unsloth** (training tools & LoRA insights) * **RunPod** (GPU compute credits) **Apache-2.0** * **v0.1.0-beta:** Initial release with reference-swap voice cloning