Multimodal

Speech-to-text (transcription)

Converting spoken audio into written text.

Transcription is usually priced per minute or per hour of audio, often well under a cent per minute. Accuracy depends on audio quality, accents and language; Arabic-specific models exist.

All terms

Frequently asked questions

What does Speech-to-text (transcription) mean?

Converting spoken audio into written text. Transcription is usually priced per minute or per hour of audio, often well under a cent per minute. Accuracy depends on audio quality, accents and language; Arabic-specific models exist.