Flux is Deepgram's speech to text model. Conversational speech recognition model built specifically for real-time voice agent applications, prioritizing low-latency and turn-aware transcription.
Specifications
Canonical IDdeepgram-flux
TypeSpeech to Text
StatusActive
CreatorDeepgramDeepgram
Providers
Input ModalitiesAudio
Output ModalitiesText

Capabilities

Input1/5
Text·
Image·
Audio✓
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Audio In
$ / min
Cloudflare Workers AI logo
Cloudflare Workers AI
@cf/deepgram/flux
$0.0077

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Flux————Current
Base ConversationalAI————Available
Base Finance————Available
Base General————Available
Base Meeting————Available
Base Phonecall————Available
Base Video————Available
Base Voicemail————Available
Deepgram Base————Available
Deepgram Enhanced————Available
Detect Entities————Available

Model IDs

@cf/deepgram/flux
deepgram-flux