F
PRODUCT DETAILS
Fish Audio Realtime STT
Realtime speech-to-text for voice agents, $0.36 an hour
- Launch date · UTC
- 2026-10-31
- Domain
- —
- Domain ending
- —
- Category
- Artificial intelligence
About this product
Fish Audio Realtime Speech to Text (transcribe-stream-1, in preview) streams audio over a WebSocket and returns transcripts turn by turn. It detects when the user has finished, tells speech from background noise, and recognizes backchannels like “mm-hm”. Per the docs, first draft text arrives about 0.5 seconds after speech starts. Supports 29 language codes, custom vocabulary, speaker tags and 8 to 48 kHz PCM audio. $0.36 per hour.
Keywords
real-time transcriptionSpeech Recognitionvoice agent