Flux Feature Overview
Below is a matrix of Deepgram’s Flux Speech-to-text feature compatibility.
Model Selection
Custom Vocabulary
Media Input Settings
End-of-Turn Configuration
Flux’s end-of-turn detection is configurable to match your use case. Use eot_threshold
for standard turn detection, or enable eager_eot_threshold
for ultra-low latency response generation. See the End-of-Turn Configuration for detailed configuration guidance.
Control Messages
Rate Limits
For information on Deepgram’s Concurrency Rate Limits, refer to our API Rate Limits Documentation.
Deepgram Self-Hosted
Self-hosted support for Flux is coming soon!
Having challenges with performance and latency? Check out Deepgram’s Self-Hosted Solution to get the benefits of running your own hosted instance of Deepgram.