Deepgram Flux

Released
2025-10-15
Last refreshed
2026-06-29
Status
Researched 136d ago
ProprietaryCommercial use: restrictedMultimodalVisionAudio
Specifications
Released
2025-10-15
Architecture
Audio / Speech
Specialization
speech-recognition
Openness
Proprietary
License
ProprietaryRestricted
Weights
Not released
Code
Unknown
Training
Pretrained
Created by

AI-powered speech recognition and text-to-speech platform.

San Francisco, USA
Founded 2014
Website
Pricing
Audio / min
$0.0065/min

List rate of 1 route · Deepgram API

Providers(1)

About

Flux is Deepgram's conversational automatic speech recognition (CSR) model, released October 15, 2025. Built specifically for voice agents: integrates turn detection natively into the ASR model, eliminating the need for a separate VAD/endpointing layer. Achieves end-of-turn detection within 1.5s (p95) and reduces interruptions ~30% and latency 200–600ms versus traditional pipelines. Emits voice-agent events: StartOfTurn, EndOfTurn, EagerEndOfTurn, TurnResumed. English: $0.0065/min; Multilingual (10 languages, GA April 2026): $0.0078/min. API ID: flux-general-en / flux-general-multi.

Providers(1)

Compare published per-minute API pricing across 1 tracked provider route.

ProviderAudio / minRoute
Deepgram API$0.0065/min
Serverless

Capabilities

MultimodalAudio

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

flux-general-enflux-general-multi

Rankings & picks(1)