@debugginglife25: Demo of Telugu Thodu built using @SarvamAI Speech-to-text system seamlessly translates Telugu to English, accurately ha…
Summary
A demo of Telugu Thodu, an app built using SarvamAI's speech-to-text system that translates Telugu to English with high accuracy, handling pauses and nuances.
View Cached Full Text
Cached at: 06/03/26, 01:41 AM
Demo of Telugu Thodu built using @SarvamAI
Speech-to-text system seamlessly translates Telugu to English, accurately handling audio pauses and capturing subtle nuances with remarkable precision. Loved it ❤️
@SarvamForDevs https://t.co/hfecQQOkSc
Vishal Singh (@debugginglife25): Helping Telugu NRIs with ageing parents in India.
Built with the awesome @SarvamAI models.
@SarvamForDevs
Similar Articles
@HarshalsinghCN: I built an open-source Hinglish TTS that beats every model on the market. I had zero research background. last week I w…
A developer documents building an open-source Hinglish text-to-speech system that outperforms existing models by fixing upstream inference bugs and adding a lightweight preprocessing wrapper, achieving high quality without training or GPU resources.
@PrajwalTomar_: THIS IS CRAZY. I connected ElevenLabs to Lovable and built an AI storytelling app in UNDER 20 minutes. Enter a kid's na…
Prajwal Tomar demonstrates how to quickly build an AI-powered storytelling app using ElevenLabs for text-to-speech and Lovable for app development, enabling personalized stories with narration and sound effects.
@SarvamAI: We're open-sourcing two frameworks for evaluating Indian ASR, and a full guide on evaluation across 22 languages. WER (…
SarvamAI releases open-source evaluation frameworks and a guide tailored for 22 Indian languages, addressing limitations of standard WER/CER metrics.
SamaVaani: Auditing and Debiasing Multilingual Clinical ASR for Indian Languages
This paper audits multilingual clinical ASR systems on psychiatric interviews in Indian languages and proposes SamaVaani, a unified debiasing technique to improve performance and fairness across demographic groups.
@alamin_ai_: OMG, guys, this is unbelievable Please listen to the Levantine Arabic and the seamless code-switching with english, a 7…
A significant breakthrough in Levantine Arabic speech synthesis and English code-switching, achieving a 76% improvement using a single RTX 3060 in an evening.