Trendora

Speech-to-text

Assess

Techniques

Technology that converts spoken audio into written text.

Why it's here

Placed in Assess: 2 article(s) of evidence from 2 source(s), led by open-source activity, with 1 in the last 30 days. Confidence 41%.

Evidence (2)

  • 3Hacker News·6/12/2026open_source
    Local CLI removes filler words from speech

    The post introduces a local command-line tool that strips filler words such as "um," "uh," and "erm" from recorded speech. The article frames the task as harder than it first appears because reliable editing must handle timing, transcript alignment, and natural-sounding output.

  • 7OpenAI Blog·5/7/2026model_release
    OpenAI Adds New Realtime Voice Models to Its API

    OpenAI has introduced new realtime voice models in its API that can reason, translate, and transcribe speech. The update is aimed at enabling more natural and intelligent voice-based applications for developers.