As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/deepgram-flux/

# Deepgram Flux (conversational STT, English + Multilingual)

Deepgram, Flux family. Status: current. Type: speech and audio. Released: 2025-10-02.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Deepgram API | `flux-general-en` | wss://api.deepgram.com/v2/listen | https://developers.deepgram.com/docs/flux/quickstart |
| Deepgram API | `flux-general-multi` | wss://api.deepgram.com/v2/listen | https://developers.deepgram.com/docs/models-languages-overview |

## Pricing

- Per minute: $0.0065
- Unit as published: per minute streaming, pay-as-you-go (flux-general-en); Flux Multilingual $0.0078/min; Growth plan $0.0057 / $0.0068
- Source: https://deepgram.com/pricing
- Last checked: 2026-09-29

## Specs

- Input: audio
- Output: text
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer speech and audio models in the registry since its release: 82. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Before it from Deepgram: Deepgram Aura-2 (2025-04-15) https://postcutoff.com/m/deepgram-aura-2/
- After it from Deepgram: Deepgram Flux TTS (2026-08-12) https://postcutoff.com/m/deepgram-flux-tts/
- Closed weights; access is hosted only.

## What stands out

- Conversational speech recognition with model-native turn-taking (first): Recognition model itself decides end-of-turn using acoustic + semantic cues (~260 ms end-of-turn detection), with EagerEndOfTurn events to start the LLM early; tunable eot_threshold, eager_eot_threshold, eot_timeout_ms. Source: https://deepgram.com/learn/introducing-flux-conversational-speech-recognition
- Multilingual conversational STT with in-call code-switching (first) (found after launch): Flux Multilingual (GA 2026-04-29): English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, Dutch with automatic language switching mid-conversation; turn detection under 400 ms. Billed by Deepgram as the world's first multilingual conversational speech recognition model. Source: https://deepgram.com/learn/deepgram-launches-flux-multilingual-press-release

## Notes

'First' claims are Deepgram's own marketing (launched at VapiCon 2025-10-02 as 'world's first conversational speech recognition model'). Uses /v2/listen (not /v1). Mid-stream numeral toggle added 2026-09-25. Companion TTS: deepgram-flux-tts.

STT built for voice agents: transcription + end-of-turn detection in one model.

Sources: https://developers.deepgram.com/docs/flux/quickstart , https://deepgram.com/pricing , https://developers.deepgram.com/changelog

Model page: https://postcutoff.com/m/deepgram-flux/