DubX: Next generation of TTS models

TTS turns written words into spoken languages that sound just like a person talking.

Jul 27 • 

Amartya Roy Chowdhury

January 2025

Notes on building in AI in 2024

Learnings on building and scaling our speech products

Jan 2 • 

Varshul

4

October 2024

[Beta] Foundational Speech Model for India

Building the Future of Multilingual AI: Foundational Speech Models for India"

Oct 10, 2024 • 

Jaskaran Singh

, 

Varshul

, and 

Raghav Prabhakar

4

February 2024

Research to Production - NeoDub

scaling in-house tech to a million users!

Feb 16, 2024 • 

Jaskaran Singh

3

Pioneering Translation Benchmarking with LLMs

NMT for Indic LLMs?

Feb 9, 2024 • 

Tanay Rathore

 and 

Sambbhav Garg

1

October 2023

Evals are all we need

voice models are having their "stable diffusion moment"

Oct 26, 2023 • 

Tanay Rathore

3

A State-of-the-Art Survey of Text-to-Speech Technology 2023

Speaking Machines: Foundation Audio Generation Models

Oct 24, 2023 • 

Jaskaran Singh

8

Running RVC Models on the Easy GUI

How to run this on Colab after Google Banned Gradio UIs

Oct 13, 2023 • 

Tanay Rathore

4

September 2023

Converging to Multi-Modal Generative AI

Single Foundational Model to rule them all

Sep 7, 2023 • 

Jaskaran Singh

4

August 2023

Contextual Translations - Attempt 1

The case for an in-house LLM for translation

Aug 29, 2023 • 

Nitin Surya

 and 

Ruchir Kumbhare

2

Self Supervised Learning (SSL)

"Unlocking Powerful Representations: The Frontier of Self-Supervised Learning"

Aug 9, 2023 • 

Jaskaran Singh

6

July 2023

Whisper's Word-Level Timestamps are Out

Bid farewell to extensive waiting periods—finally, it has arrived!

Jul 26, 2023 • 

T. Pranav

6