# indic-parler-tts by AI4Bharat: Open-Weight Model Source: https://savrn.com/models/indic-parler-tts Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve indic-parler-tts (938M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 1.9 GB | 2.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.9 GB | 1.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.5 GB | 0.6 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 22, 2026. [indic-parler-tts on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/indic-parler-tts/gpus) ## SAVRN's Notes on indic-parler-tts Indic Parler-TTS speaks Indian languages and English, and it lets you describe the voice you want in plain text: speaker, pace, pitch and recording quality. AI4Bharat fine-tuned it on 1,806 hours of multilingual Indic and English speech. At 938M parameters it needs about 2 GB at 16-bit. Apache 2.0 allows commercial use. For services that must speak to users across India in their own language, this is the most complete open option in our catalog; test it on the specific languages and dialects you serve. SAVRN Research, 2026-09-18 ## Model Card By AI4Bharat, published under apache-2.0, revision 7b527af5ee8e. Indic Parler-TTS is a multilingual Indic extension of [Parler-TTS Mini](https://huggingface.co/parler-tts/parler-tts-mini-v1.1). It is a fine-tuned version of [Indic Parler-TTS Pretrained](https://huggingface.co/ai4bharat/indic-parler-tts-pretrained), trained on a 1,806 hours multilingual Indic and English dataset. Indic Parler-TTS Mini can officially speak in 20 Indic languages, making it comprehensive for regional language technologies, and in English. The 21 languages supported are: Assamese, Bengali, Bodo, Dogri, English, Gujarati, Hindi, Kannada, Konkani, Maithili, Malayalam, Manipuri, Marathi, Nepali, Odia, Sanskrit, Santali, Sindhi, Tamil, Telugu, and Urdu. Thanks to its better prompt tokenizer, it can easily be extended to other languages. This tokenizer has a larger vocabulary and handles byte fallback, which simplifies multilingual training. This work is the result of a collaboration between theHuggingFace audio team and the [AI4Bharat](https://ai4bharat.iitm.ac.in/) team. ### Quick Index - Installation - Key capabilities - Using a random voice - Switching languages - Using a specific speaker - Some Description Examples - Evaluation - Motivation - [Optimizing inference](https://github.com/huggingface/parler-tts/blob/main/INFERENCE.md) #### Installation Using Parler-TTS is as simple as "bonjour". Simply install the library once: [Read the full model card (2,328 words)](https://savrn.com/models/indic-parler-tts/card) ## Identity and Version Repository ai4bharat/indic-parler-tts Publisher AI4Bharat Task Text to speech Modality Audio Library transformers Parameters 938M parameters Languages en, as, bn, gu, hi, kn, ks, or Revision 7b527af5ee8ed1f9a28d80b19703ed9bb8ba10ca First published 2024-10-28 Last updated 2025-09-24 ## Files and Weights 10 files, 3.8 GB in total. The weights are 1 file totalling 3.8 GB in safetensors. Weights1 file · 3.8 GB Configuration4 files · 8.3 KB Tokenizer3 files · 12.1 MB Documentation1 file · 24.7 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 3.8 GB | — | | config.json | Configuration | 7.3 KB | — | | generation_config.json | Configuration | 223 B | — | | preprocessor_config.json | Configuration | 206 B | — | | special_tokens_map.json | Configuration | 552 B | — | | README.md | Documentation | 24.7 KB | — | | .gitattributes | Repository | 1.5 KB | — | | tokenizer.json | Tokenizer | 10.3 MB | — | | tokenizer.model | Tokenizer | 1.8 MB | — | | tokenizer_config.json | Tokenizer | 990 B | — | ## License and Download License apache-2.0 Access Access requested at publisher Download size 3.8 GB [Request access from AI4Bharat](https://huggingface.co/ai4bharat/indic-parler-tts) AI4Bharat grants access through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by arXiv:2402.01912 - Trained on (disclosed) ai4b-hf/GLOBE-annotated ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 3.8 GB | | 16-bit | 1.9 GB | | 8-bit | 0.9 GB | | 4-bit | 0.5 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About indic-parler-tts ### How much GPU memory does indic-parler-tts need? About 2.3 GB at 16-bit and 0.6 GB at 4-bit: the weights (938M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run indic-parler-tts on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use indic-parler-tts commercially? Yes. indic-parler-tts is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ## Similar Models Model · Text to speech ### [Qwen3-TTS-12Hz-0.6B-Base](https://savrn.com/models/qwen3-tts-12hz-0-6b-base) [Qwen](https://savrn.com/model-publishers/qwen) Qwen3-TTS is a family of advanced multilingual, controllable, robust, and streaming text-to-speech models. Trained on over 5 million hours of speech data spanning 10 languages, Qwen3-TTS supports state-of-the-art 3-second voice cloning and description-based control. This specific checkpoint is the 0.6B Base model, which is capable of rapid voice cloning from a user-provided audio input. To clone a voice and synthesize new content using the Base model, you can use the following code snippet: Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles to meet global application… Open weights apache-2.0 915M parameters [View model](https://savrn.com/models/qwen3-tts-12hz-0-6b-base) Model · Text to speech ### [Qwen3-TTS-12Hz-0.6B-CustomVoice](https://savrn.com/models/qwen3-tts-12hz-0-6b-customvoice) [Qwen](https://savrn.com/model-publishers/qwen) Qwen3-TTS is a series of advanced multilingual, controllable, robust, and streaming text-to-speech models developed by the Qwen team. This specific checkpoint is the 0.6B CustomVoice variant, based on the 12Hz tokenizer. It supports 9 premium timbres and allows for fine-grained style control over target voices via natural language instructions across 10 major languages. To use Qwen3-TTS, you can install the qwen-tts package: For Qwen3-TTS-12Hz-0.6B-CustomVoice, the following speakers are supported. We recommend using each speaker’s native language for the best results: If you find Qwen3-TTS useful for your research, please consider citing Open weights apache-2.0 906M parameters [View model](https://savrn.com/models/qwen3-tts-12hz-0-6b-customvoice) Model · Text to speech ### [qwen-tts-ngoc-huyen-voice](https://savrn.com/models/qwen-tts-ngoc-huyen-voice) [NGUYEN HUU TAM](https://savrn.com/model-publishers/huutamm1612) This Vietnamese text-to-speech model is fine-tuned from g-group-ai-lab/gwen-tts-0.6B, based on the Qwen3-TTS architecture. The exported package includes merged weights and the ngochuyen speaker in CustomVoice mode. No reference audio is required at inference time. The model was fine-tuned on approximately 90 hours of Ngọc Huyền's voice, collected by crawling YouTube and TikTok. Training used LoRA adaptation, adapter merging, and selective refinement of the talker and output head, followed by joint refinement with the code predictor. The final model was selected by the training pipeline and packaged with a speaker embedding derived from reference audio. If the repository is private… Open weights 906M parameters [View model](https://savrn.com/models/qwen-tts-ngoc-huyen-voice) Model · Text to speech ### [VibeVoice-Realtime-0.5B](https://savrn.com/models/vibevoice-realtime-0-5b) [Microsoft](https://savrn.com/model-publishers/microsoft) VibeVoice-Realtime is a lightweight real‑time text-to-speech model supporting streaming text input and robust long-form speech generation. It can be used to build realtime TTS services, narrate live data streams, and let different LLMs start speaking from their very first tokens (plug in your preferred model) long before a full answer is generated. It produces initial audible speech in ~300 ms (hardware dependent). ▶ Watch demo video (Launch your own realtime demo via the websocket example in Usage) Although the model is primarily built for English, we found that it still exhibits a certain level of multilingual capability—and even performs reasonably well in some languages. We provide nine… Open weights mit 1B parameters transformers [View model](https://savrn.com/models/vibevoice-realtime-0-5b) Model · Text to speech ### [microsoft__VibeVoice-Realtime-0.5B](https://savrn.com/models/microsoft-vibevoice-realtime-0-5b) [Allinsama](https://savrn.com/model-publishers/allinsama) VibeVoice-Realtime is a lightweight real‑time text-to-speech model supporting streaming text input and robust long-form speech generation. It can be used to build realtime TTS services, narrate live data streams, and let different LLMs start speaking from their very first tokens (plug in your preferred model) long before a full answer is generated. It produces initial audible speech in ~300 ms (hardware dependent). ▶ Watch demo video (Launch your own realtime demo via the websocket example in Usage) Although the model is primarily built for English, we found that it still exhibits a certain level of multilingual capability—and even performs reasonably well in some languages. We provide nine… Open weights mit 1B parameters transformers [View model](https://savrn.com/models/microsoft-vibevoice-realtime-0-5b) Model · Text to speech ### [SemBridge](https://savrn.com/models/sembridge) [ASLP-lab](https://savrn.com/model-publishers/aslp-lab) SemBridge bridges discrete semantic supervision and continuous acoustic generation. A shared semantic tokenizer anchors both acoustic latents and autoregressive language-model states, improving linguistic fidelity while retaining continuous-latent generation. The unified model supports text-to-speech, note-conditioned singing, and mixed speech and singing. - [2026-10]: Released the inference code and model checkpoints. - [2026-08]: Released the arXiv paper. Use Python 3.10. The repository includes 10 complete examples from our Demo page: 4 TTS, 4 SVS, and 2 Unified cases, with reference audio and prepared requests. SVS and Unified include aligned lyrics, pitches, durations, and… Open weights apache-2.0 818M parameters 32,768 tokens [View model](https://savrn.com/models/sembridge) ## AI4Bharat [All models and datasets](https://savrn.com/model-publishers/ai4bharat) ## Versions - [7b527af5ee8e](https://savrn.com/models/indic-parler-tts/versions/7b527af5ee8e) · current 2026-09-18 ## Explore More - [All text to speech models](https://savrn.com/models/tasks/text-to-speech) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-20. - [Hugging Face record](https://huggingface.co/ai4bharat/indic-parler-tts) - [How the hub is built](https://savrn.com/model-hub/methodology)