Deepgram's Self-Hosted Speech-to-Text runs its speech recognition models on customer-controlled infrastructure.
Deepgram's self-hosted offering deploys its speech-to-text models in the customer's own environment, either on-premises or in a private cloud. Deployment runs through containers and Kubernetes, and audio stays within the customer environment rather than leaving for a provider-hosted service.
The offering targets organizations with data-residency or security constraints that still need low-latency real-time transcription.
| Attribute | Deepgram Self-Hosted Speech-to-Text | On-Device Speech-to-Text | |
|---|---|---|---|
| Provider |  |  | |
| Founded | 2015 | 2006 | |
| Sells To | Enterprise, Small Business | — | |
| Pricing Model | Recurring, Software, Usage-based | Recurring Subscription | |
| Ownership | Venture-backed | Private |
Provider
Founded 2015
Sells To Enterprise, Small Business
Pricing Model Recurring, Software, Usage-based
Ownership Venture-backed
Provider
Founded 2006
Sells To —
Pricing Model Recurring Subscription
Ownership Private
Speechmatics' Speech-to-Text API is a multilingual automatic speech recognition service offered in real-time and batch modes with speaker diarization.
AssemblyAI's Speech-to-Text API transcribes audio in streaming and pre-recorded modes with speaker diarization.
Agent STT is a real-time speech-to-text API package built for AI voice agent workloads.
Self-managed machine translation server deployed behind the customer's own firewall.
Offline-capable voice-to-text software that types polished text into any app.
Speechmatics' Speech-to-Text API is a multilingual automatic speech recognition service offered in real-time and batch modes with speaker diarization.
AssemblyAI's Speech-to-Text API transcribes audio in streaming and pre-recorded modes with speaker diarization.
Agent STT is a real-time speech-to-text API package built for AI voice agent workloads.
Self-managed machine translation server deployed behind the customer's own firewall.
AI dictation software that turns spoken words into formatted text in any app.
Offline-capable voice-to-text software that types polished text into any app.
