GenAIWiki
Models

Speech-to-text

Speech-to-text, or ASR, converts audio into text, optionally with timestamps, speakers, and punctuation.

Expanded definition

Automatic speech recognition models transcribe live or recorded audio. Quality depends on language, domain vocabulary, overlap, and noise. Production stacks add diarization, custom terms, PII redaction, and streaming vs batch modes. On GenAIWiki this maps to models such as Whisper, Gemini 3.5 Transcribe, and MAI-Transcribe. Transcription is not understanding; summarization and action items are a second model pass.

Related terms

Explore adjacent ideas in the knowledge graph.

Speech-to-text FAQ

What is Speech-to-text?

Speech-to-text, or ASR, converts audio into text, optionally with timestamps, speakers, and punctuation.

How is Speech-to-text used in AI systems?

Automatic speech recognition models transcribe live or recorded audio. Quality depends on language, domain vocabulary, overlap, and noise. Production stacks add diarization, custom terms, PII redaction, and streaming vs batch modes. On GenAIWiki this maps to models such as Whisper, Gemini 3.5 Transcribe, and MAI-Transcribe. Transcription is not understanding; summarization and action items are a...

Related

Comparisons, tools, and models that connect to this idea.