Speech-to-text

Model API

Streaming speech-to-text API with semantic turn detection, keyword boosting and tunable latency over one WebSocket.

Find alternatives to Speech-to-text

TypeModel API
RoleHosted model API
AvailabilitySold
DeploymentSaaS
Intended for—
SecurityNot recorded
StatusActive
Sold withinSold on its own
PricingFreemium, Subscription — official pricing ↗

What it does

gradium.ai

Sources

Pricing

Pricing page · 16 Nov 2026

Pricing page, Free plan card: "Free $0 /mo 45k credits/mo Start free Includes Text-to-Speech Speech-to-Text Voice Design"; the paid plans (XS, S, M, L) are each labelled "Everything in" the one below, plus more credits.

Description

Official documentation · 16 Nov 2026

Page quote: "Streaming transcription that knows when your user is done talking, and learns your pronunciation. Semantic turn detection, keyword boosting and tunable latency over one WebSocket."

What it does

Official documentation · 16 Nov 2026

Page quote: "Streaming transcription that knows when your user is done talking, and learns your pronunciation. Semantic turn detection, keyword boosting and tunable latency over one WebSocket."

Sold within

Pricing page · 16 Nov 2026

Pricing page, Free plan card: "Free $0 /mo 45k credits/mo Start free Includes Text-to-Speech Speech-to-Text Voice Design"; the paid plans (XS, S, M, L) are each labelled "Everything in" the one below, plus more credits. Each plan has a self-serve "Select" or "Start free" button.

Name

Official documentation · 16 Nov 2026

Models menu label "Speech-to-text" on the pricing page and the product page heading.

URL

Official documentation · 16 Nov 2026

Page quote: "Streaming transcription that knows when your user is done talking, and learns your pronunciation. Semantic turn detection, keyword boosting and tunable latency over one WebSocket."

Deployment

Official documentation · 16 Nov 2026

Page quote: "Streaming transcription that knows when your user is done talking, and learns your pronunciation. Semantic turn detection, keyword boosting and tunable latency over one WebSocket." The pages read describe a vendor-run web service and no other deployment model, so saas is the vendor-operated reading.

Interfaces

Official documentation · 16 Nov 2026

Product page: "Semantic turn detection, keyword boosting and tunable latency over one WebSocket."

Also from Gradium

Open Gradium in the directory

Something wrong here? Send a correction — quote this product id: gradium-speech-to-text.