Deepgram Flux Models by Deepgram
1 model2025
Last refreshed 2026-06-29. Next refresh: weekly.
Details
ResearcherDeepgram
LicenseProprietary
Commercial useCommercial use: conditional
Models1
Released2025
Capabilities
MultimodalAll models
Links
WebsiteAbout
Deepgram's Flux family provides conversational speech recognition for voice agents, combining ASR with model-native end-of-turn detection.
Decision facts
- Best fit
- audiospeech recognitionvision and multimodal work
- Capability starting point
- Deepgram Flux with multimodal inputs
- Lowest tracked input
- Not tracked
- Closest related family
- MOSS-TTS
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
Deepgram FluxCurrent
Use when the workload needs speech recognition, multimodal inputs, and audio.
2025-10speech recognitionmultimodal inputsaudio
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Deepgram Flux | Use when the workload needs speech recognition, multimodal inputs, and audio. | 2025-10 | speech recognitionmultimodal inputsaudio | Current |
Release Timeline
1 release group2025-10
1 current
Deepgram Flux
Currentspeech recognitionmultimodal inputsaudio
Specifications(1 models)
| Model | Released | Multimodal |
|---|---|---|
| Deepgram Flux | 2025-10 | Yes |
