Rime Speech-to-Text
Streaming and whole-file speech-to-text API for voice agents that transcribes English or Spanish speech into partial and final transcripts, in written or word-for-word mode with custom terms, through an SDK, WebSocket or gRPC, in the cloud, a VPC or on-premises.
Find alternatives to Rime Speech-to-Text
What it does
- Speech to text
Sources
- Pricing
-
Official documentation · 21 Oct 2026
Pay-as-you-go rate card: Rime STT "$0.002 / min from Nov 20", free until November 19; Enterprise "Volume rates from Nov 20" on an annual commitment. The launch-period free use is a promotion, so no free model is claimed.
- Description
-
Official documentation · 21 Oct 2026
"Rime speech-to-text turns English or Spanish speech into text. It returns partial transcripts while the person speaks." Settings (word-for-word or written mode, custom terms) are on the same page; the pricing page (https://www.rime.ai/pricing) lists custom vocabulary of up to 1,024 characters per request.
- What it does
-
Official documentation · 21 Oct 2026
"Rime speech-to-text turns speech into text for voice agents."
- Sold within
-
Official documentation · 21 Oct 2026
Sold on its own: a Pay as you go plan with the line "Metered by the minute, billed monthly to your card" and its own rate row for Rime STT; no parent product is named.
- Name
-
Official documentation · 21 Oct 2026
Pricing page rate-card row "Rime STT" ("$0.002 / min from Nov 20"); the launch post and docs call it Rime Speech-to-Text.
- URL
-
Official documentation · 21 Oct 2026
Rime's documentation overview of its speech-to-text service: "Rime speech-to-text turns English or Spanish speech into text." It is announced on the vendor's launch post https://www.rime.ai/resources/rime-announces-stt, carried as a banner on every rime.ai page (the banner text reads Rime speech-to-text is here, https://www.rime.ai/) and as its own column and rate on https://www.rime.ai/pricing.
- Deployment
-
Official documentation · 21 Oct 2026
In the speech-to-text comparison the page lists "Same deployment as Rime TTS" with a tick, under "Deploy on-prem, VPC, or cloud" (cloud API, VPC or on-premises).
- Interfaces
-
Official documentation · 21 Oct 2026
Three ways to connect in the docs table: "Rime SDK (recommended)" (Python, Node.js, Go or Rust), "WebSocket API" and "gRPC API".
- Modalities
-
Official documentation · 21 Oct 2026
Audio in, text out: the service takes "Headerless PCM16 at 16 kHz, mono" audio (or one WAV file) and "returns partial transcripts while the person speaks" and then a final transcript.
- Intended for
-
Official documentation · 21 Oct 2026
Backend developers building voice agents: the page tells the reader to "Use the Rime SDK if your backend is in a language that the SDK supports."
Also from Rime
-
Mist / Coda API service
Text-to-speech voice models sold by API, or self-hosted, to teams building enterprise voice agents; priced per character.
Something wrong here? Send a correction — quote this product id: rime-speech-to-text.