Deepgram's Speech-to-Text API is a conversational speech recognition service in real-time and pre-recorded modes.
The Speech-to-Text API provides conversational speech recognition for developers and enterprise teams, with real-time streaming and pre-recorded transcription modes. It includes turn detection and interruption handling for voice-agent interactions, speaker diarization to separate participants, and latency in the sub-300 millisecond class for interactive use cases.
The service can be deployed in the cloud or self-hosted on customer infrastructure, and Deepgram positions it for developer platforms and enterprise contact-center, meeting, and voice-agent applications.
| Attribute | Deepgram Speech-to-Text API | Agent STT, Speech-to-Text API | Ink | |
|---|---|---|---|---|
| Provider |  |  |  | |
| Founded | 2015 | 2006 | 2023 | |
| Sells To | Enterprise, Small Business | — | Enterprises | |
| Pricing Model | Recurring, Software, Usage-based | Recurring Subscription | Recurring, Software | |
| Ownership | Venture-backed | Private | 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
Provider
Founded 2023
Sells To Enterprises
Pricing Model Recurring, Software
Ownership Private
AssemblyAI's Speech-to-Text API transcribes audio in streaming and pre-recorded modes with speaker diarization.
AssemblyAI Realtime converts streaming audio into text for voice agents with low-latency partial and final transcripts.
Scribe is ElevenLabs speech-to-text for live transcription under 150 milliseconds in agent and real-time applications.
On-Device Speech-to-Text is a speech recognition offering for Mac and Windows that processes audio locally.
OpenAI Realtime API provides conversational speech-to-speech models for developers building interactive voice agents.
Developer API for streaming real-time speech-to-speech translation and dubbing over WebSocket.
Developer API platform for production-ready speech, transcription, music, agents, and audio generation.
Offline-capable voice-to-text software that types polished text into any app.
Gemini Live API enables real-time voice and vision interactions through streaming conversational models.
Voice-to-text software that turns speech into formatted writing across apps.
Text to Speech is a speech synthesis API for voice agents and real-time applications.
AssemblyAI's Speech-to-Text API transcribes audio in streaming and pre-recorded modes with speaker diarization.
AssemblyAI Realtime converts streaming audio into text for voice agents with low-latency partial and final transcripts.
Scribe is ElevenLabs speech-to-text for live transcription under 150 milliseconds in agent and real-time applications.
On-Device Speech-to-Text is a speech recognition offering for Mac and Windows that processes audio locally.
OpenAI Realtime API provides conversational speech-to-speech models for developers building interactive voice agents.
Developer API for streaming real-time speech-to-speech translation and dubbing over WebSocket.
Developer API platform for production-ready speech, transcription, music, agents, and audio generation.
Offline-capable voice-to-text software that types polished text into any app.
Gemini Live API enables real-time voice and vision interactions through streaming conversational models.
Voice-to-text software that turns speech into formatted writing across apps.
Text to Speech is a speech synthesis API for voice agents and real-time applications.
Programmable voice APIs for making, receiving, and managing phone calls globally.
