Modalities
Speech-to-Text
AI that converts spoken audio into written text — the technology behind voice assistants, transcription tools, and meeting recorders.
01 ——
In plain English
Speech-to-text — also called Automatic Speech Recognition (ASR) — is AI that turns recorded or live audio of human speech into written text. It powers transcription services, voice assistants, captioning, and voice control.
Common applications:
- Meeting transcripts — Otter, Fireflies, Granola
- Voice assistants — Siri, Alexa, ChatGPT voice
- Subtitles & captions — YouTube, Zoom, podcasts
- Voice typing — dictation in docs, emails, code editors
- Call analytics — sales call coaching, support QA
Modern ASR: OpenAI's Whisper transformed the field in 2022 — open-source, multilingual, and highly accurate. Most modern transcription products either use Whisper or one of its competitors (AssemblyAI, Deepgram, Google's Chirp).
Quality is now near-human for clean English audio; accents, multiple speakers, and noisy environments remain harder.
02 ——
Related terms
Text-to-Speech
AI that converts written text into natural-sounding spoken audio — used for narration, accessibility, voice assistants, and content creation.
Conversational AI
AI systems designed for natural back-and-forth dialogue with users — covering chatbots, voice assistants, and AI agents.
Multi-modal
An AI model that can understand and work with multiple types of input — text, images, audio, or video — not just text.
Voice Cloning
AI that learns to mimic a specific person's voice from a short sample, then generates new speech in that voice from any text.
Back to glossaryLast reviewed May 2026