Flux Multilingual & Language Prompting
Flux Multilingual & Language Prompting
Use Flux Multilingual with language hints to get near-monolingual accuracy in 10 languages, or let the model auto-detect.
Flux Multilingual & Language Prompting
Use Flux Multilingual with language hints to get near-monolingual accuracy in 10 languages, or let the model auto-detect.
Flux Multilingual (flux-general-multi) is a single model supporting 10 languages with the same turn-aware, interruption-aware conversational intelligence as flux-general-en. The optional language_hint parameter biases the model toward specific languages, delivering accuracy on par with dedicated monolingual models. Without hints, the model auto-detects the spoken language.
Flux Multilingual uses the same production endpoint and API key you already use for Flux. Just set model=flux-general-multi — no new credentials or endpoints required. Pricing is the same as flux-general-en.
An EU endpoint is also available: wss://api.eu.deepgram.com/v2/listen?model=flux-general-multi
Flux Multilingual is available on the hosted API, on self-hosted deployments, and in the latest Deepgram SDKs:
deepgram-sdk v7.0.0+@deepgram/sdk v5.1.0+deepgram-java-sdk v0.3.0+Use language_hint values when you connect, and use language_hints in Configure messages to update them
mid-stream. See the SDK examples below for the syntax in each SDK.
Locale-level subtags (e.g., en-GB, pt-BR) are accepted. If no exact match exists, Flux treats them as the base language code.
language_hint Parameterlanguage_hint string (optional, repeatable)
Pass one or more language_hint values to bias the model toward specific languages. This improves accuracy when you know the expected language(s) ahead of time.
language_hint is only supported on flux-general-multi. Sending it to any other model (including flux-general-en) returns a 400 error.
Existing Flux concurrency limits now apply across both flux-general-en and flux-general-multi (shared pool). See API Rate Limits for details.
When you know the caller’s language ahead of time (e.g., a Spanish-language call center), set a single language_hint for best accuracy.
When callers may speak one of several languages (e.g., a bilingual English/Spanish support line), pass multiple hints. The model biases toward the specified set while still producing accurate transcripts regardless of which language is spoken.
When you have no knowledge of what language the caller will speak, omit language_hint entirely. The model auto-detects the language from the audio.
When speakers switch between languages mid-conversation (e.g., a bilingual speaker mixing English and Spanish), set hints for the expected languages. Flux handles mid-sentence language switches natively.
When using flux-general-multi, all TurnInfo events include two additional fields:
Use the languages field to route downstream processing — for example, selecting the correct TTS voice or LLM prompt language based on what the user actually spoke.
You can update language hints during a stream using the Configure control message without disconnecting. This is useful when conversational context changes — for example, after detecting the caller’s language, you can narrow the hints for better accuracy.
A common voice agent pattern is to start a call with broad language detection, then lock in the detected language for the rest of the conversation. This gives you the best of both worlds: flexible auto-detection at the start and high-accuracy single-language transcription once the caller’s language is known.
How it works:
languages field from the first EndOfTurn event to identify the caller’s language.languages, send another Configure to update the hint.Step 1 — Connect with broad detection:
Or, if you know callers will speak one of a few languages, start with a subset:
Step 2 — Read the detected language from the first EndOfTurn:
The first entry in languages is the primary language by word count.
Step 3 — Lock in the detected language:
This biases all subsequent transcription toward Spanish, improving accuracy for the rest of the call.
Step 4 — Handle language switches (optional):
If a later turn returns a different primary language, update the hint:
Locking in a single language after detection delivers the best accuracy — comparable to using a dedicated monolingual model. For calls where code-switching is expected throughout, keep multiple hints active instead of locking to one language.
Example error response:
flux-general-enflux-general-en remains available and recommended for English-only workloads. Use flux-general-multi when you need multilingual support or expect non-English audio. Both models share the same turn detection architecture, end-of-turn configuration, and control message interface.