Indian Flag
Government Of India
A-
A
A+
Home/Models/BharatGen Multilingual TTS - Sooktam2

BharatGen Multilingual TTS - Sooktam2

Sooktam-2 is a multilingual Indic Text-to-Speech model by BharatGen supporting 12 languages including Hindi, Marathi, Tamil, Telugu, Bengali, Urdu, Punjabi and Indian English. It enables high-quality speech synthesis with reference-guided voice conditioning, preserving speaker voice, accent and prosody for natural and expressive generation.

About Model

Sooktam-2 is a sovereign multilingual Text-to-Speech (TTS) model developed by BharatGen. It generates natural and expressive speech across major Indian languages using reference-guided voice conditioning, preserving the speaker’s voice, accent, and cultural cadence. Supported Languages (12) Hindi · Marathi · Gujarati · Tamil · Telugu · Kannada · Bengali · Malayalam · Odia · Urdu · Punjabi · Indian English Key Capabilities Reference-guided voice cloning Multilingual Indic speech synthesis Natural prosody and expressive speech generation Language-aware CLS tokenization for accurate Indic phonetics Production-ready audio quality for scalable deployment

BharatGen Multilingual TTS - Sooktam2

Metadata Metadata

Other

bharatgenai

Transformers

PyTorch

Restricted

BharatGen

Other

09/03/26 08:11:25

Vansh Pundir

1.25 GB

config.json ( 334 Bytes )

To preview this file, you need to be a registered user. Please complete the registration process to gain access and continue viewing the content.

Activity Overview Activity Overview

  • Downloads0
  • Downloads 9
  • File Size 1.25 GB
  • Views 602

Tags Tags

  • multilingual-TTS
  • Text-to-Speech
  • Multilingual Speech
  • Audio Synthesis
  • sooktam2

License Control License Control

Other

Version Control Version Control

FolderVersion 1(1.25 GB)
  • Vansh Pundir·1 month(s) ago
    • application/json
      config.json
    • undefined
      hf_auto.py
    • undefined
      sooktam.safetensors
    • undefined
      test.py

More Models from BharatGen More Models from BharatGen

Param2-17B-Thinking
BharatGen presents Param-2-17B-MoE-A2.4B, a large-scale Mixture-of-Experts (MoE) language model designed to deliver high model capacity while retaining the inference efficiency of a much smaller dense model. It uses a Hybrid MoE architecture with 17B total parameters, while activating only 2.4B parameters per token.
pretrained
Mixture of Experts
Multilingual Text
  • See Upvoters1
  • Downloads29
  • File Size57.29 GB
  • Views838
Updated 1 month(s) ago
BHARATGEN
View Details
share
BharatGen Multilingual TTS - Sooktam2
Sooktam-2 is a multilingual Indic Text-to-Speech model by BharatGen supporting 12 languages including Hindi, Marathi, Tamil, Telugu, Bengali, Urdu, Punjabi and Indian English. It enables high-quality speech synthesis with reference-guided voice conditioning, preserving speaker voice, accent and prosody for natural and expressive generation.
Text-to-Speech
multilingual-TTS
sooktam2
Audio Synthesis
Multilingual Speech
  • See Upvoters0
  • Downloads9
  • File Size1.25 GB
  • Views603
Updated 1 month(s) ago
BHARATGEN
View Details
share
BharatGen - Param-1-7B-MoE Advancing Multilingual GenAI for India
Param-1-7B-MoE is a multilingual large language model developed under the Param-1 family as part of BharatGen – A Suite of Generative AI Technologies for India. With 7 billion parameters and a Mixture of Experts (MoE) architecture, the model is designed to better understand and generate text across English, Hindi, and 14 additional Indian languages. The model is pretrained from scratch with a strong focus on linguistic diversity, cultural context, and large-scale multilingual representation.
safetensors
mixtral
region:us
  • See Upvoters1
  • Downloads79
  • File Size0
  • Views1,116
Updated 3 month(s) ago
BHARATGEN
View Details
share
A2TTS-Malayalam Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
SpeechSynthesis
multilingual-TTS
TextToSpeech
  • See Upvoters0
  • Downloads16
  • File Size1.62 GB
  • Views1,623
Updated 9 month(s) ago
BHARATGEN
View Details
share
A2TTS-Gujarati Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
SpeechSynthesis
TextToSpeech
multilingual-TTS
  • See Upvoters1
  • Downloads22
  • File Size1.62 GB
  • Views3,284
Updated 9 month(s) ago
BHARATGEN
View Details
share
A2TTS-Telugu Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
SpeechSynthesis
multilingual-TTS
TextToSpeech
  • See Upvoters0
  • Downloads21
  • File Size1.62 GB
  • Views1,878
Updated 9 month(s) ago
BHARATGEN
View Details
share
A2TTS-Tamil Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
TextToSpeech
multilingual-TTS
SpeechSynthesis
  • See Upvoters0
  • Downloads49
  • File Size1.62 GB
  • Views2,854
Updated 9 month(s) ago
BHARATGEN
View Details
share
A2TTS-Punjabi Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
TextToSpeech
SpeechSynthesis
multilingual-TTS
  • See Upvoters0
  • Downloads35
  • File Size1.62 GB
  • Views1,526
Updated 9 month(s) ago
BHARATGEN
View Details
share
A2TTS-Marathi Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
TextToSpeech
SpeechSynthesis
multilingual-TTS
  • See Upvoters2
  • Downloads22
  • File Size1.62 GB
  • Views2,981
Updated 9 month(s) ago
BHARATGEN
View Details
share
A2TTS-Kannada Speaker Adaptive TTS (Text-to-Speech)-v0.5
Text-to-speech synthesis model tailored to match a given speaker's voice sample.
SpeechSynthesis
multilingual-TTS
TextToSpeech
  • See Upvoters0
  • Downloads11
  • File Size1.62 GB
  • Views1,788
Updated 9 month(s) ago
BHARATGEN
View Details
share

© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.