The company stated that the model has been trained on proprietary multilingual datasets spanning more than 1,056 domains.
Gnani.ai launches Vachana STT, a foundational Indic speech-to-text model trained on 1M hours, under the IndiaAI Mission to ...
New York, NY, Dec. 18, 2025 (GLOBE NEWSWIRE) -- Voximplant, a leading cloud communications platform, announced native support ...
Credit: Shutterstock Today marks an exciting moment for the developer community as xAI officially introduces the Grok Voice ...
This repo provides a command-line tool for performing automatic speech-to-text tasks (i.e., "transcription") using open source models from Hugging Face Hub. For interactive tasks, it allows users to ...
Obsessing over model version matters less than workflow.
Top free transcription APIs for 2025, pick accurate, scalable results for your app or AI project. Validate AI quality and ...
An ESP32 client that captures audio over I2S and posts WAV to a server. A lightweight Flask/Gunicorn server that returns JSON transcriptions via speech_recognition. Designed for deterministic embedded ...
Abstract: This letter presents a new target speech recognition problem, where the target speech is defined by a keyword. For instance, when a person speaks “Hey Google” or “Help Me”, we hope the model ...
Abstract: The speech recognition is plays a vital role in the technology. The proposed work introduces a web application that leverages state-of-the-art technologies for audio-to-text recognition and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback