Skip to content
TechIndexSubmit
Back to directory

SOV-Transcribe-1

SOV-Transcribe-1 is Salesforce's open-weight speech-augmented language model for non-streaming automatic speech recognition, offering high English transcription accuracy and multilingual support.

Similar tools

  • A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

    AI Apps
  • AccurateScribe.ai is a Freemium speech-to-text product for operators who record interviews, standups, and media and need structured transcripts they can share. It offers speaker detection, multilingual transcription, and export to TXT, DOCX, PDF, SRT, and VTT. Paid plans expand capacity as volume grows.

    AI Apps
  • tiny-voca is a fully open, 4.5M-parameter English text-to-speech AI model with two voices, designed for efficient, real-time operation on CPUs and in browsers.

    Models
  • Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

    AI Apps
  • A 29M-parameter speech-to-text model capable of outputting words before they are fully spoken. It is designed for real-time transcription and low-latency applications.

    Models
  • (NIPS 2025) OpenOmni: Official implementation of Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis

    Models