Fish Audio Realtime STT
Realtime speech-to-text for voice agents, $0.36 an hour
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Read the full description
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.
Visit website ↗ Source listing ↗
More like this: all 128 launches in speech and voice ai models →
PH · launched Oct 31, 2026 · 4 upvotes (top 7%)
- Horizontal
- Model & infra
- Developer
- AI-native
- Commercial product
- Artificial Intelligence
Similar launches
See all 493 similar launches →Could you build this?
No The product is a proprietary streaming speech recognition model with turn detection and backchannel recognition, which requires ASR research and large training data that vibe coding cannot supply.
What it would actually take: A real version needs a trained streaming ASR model with low-latency incremental decoding, end-of-turn detection, and noise and backchannel classification. That means speech ML researchers, large labeled audio corpora, and GPU inference infrastructure. Wrapping an existing ASR API would produce a thin imitation rather than the same product.
Competitors
Other products that read as similar to this one : 493 launches clear the similarity bar, closest 8 shown.
Attention rank: #41 of 494 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 358 days after the earliest competitor.
- Fish Voice · ph · 2026-10-14 · 1 upvotes · similarity 0.57
- AssemblyAI · ph · 2026-10-29 · 76 upvotes · similarity 0.57
- voisync-lite · ph · 2026-09-18 · 1 upvotes · similarity 0.54
- Orchard · ph · 2026-10-06 · 1 upvotes · similarity 0.52
- Boboyka Voice, Pay-as-u-go TTS & STT API · ph · 2026-10-20 · 1 upvotes · similarity 0.52
- ComfyUI-Drama3 · github · 2026-10-14 · 77 upvotes · similarity 0.52
- Kugel Ear · ph · 2026-10-22 · 81 upvotes · similarity 0.52
- JOBE Vox · ph · 2026-10-28 · 2 upvotes · similarity 0.51