DialNexa Supported Transcribers Reference

DialNexa supported transcribers are the speech to text options users can select for an agent version. They affect recognition accuracy, language fit, endpoint timing, interruption handling, rate preview, and the transcript evidence shown after calls.

DialNexa transcriber selector showing the Soniox option for the selected agent language.

If the transcript is wrong, the model is reasoning over the wrong story.

DialNexa Supported Transcriber Options

Display name in docs	Selector label	Provider	Model id	Best for
Deepgram Nova 3	Deepgram Nova 3	Deepgram	`nova-3`	Supported-language calls that need Nova recognition or a compatible fallback.
Deepgram Nova 2	Deepgram Nova 2	Deepgram	`nova-2`	Existing agents tuned on Nova 2 or regression checks.
Deepgram Flux	Deepgram Flux	Deepgram	`flux-general-en` or `flux-general-multi`	English calls and supported multilingual tests that need sharper turn boundaries.
Soniox STT RT v5	Soniox	Soniox	`stt-rt-v5`	Hindi-English and code-switched conversations.
Sarvam Saaras	Sarvam Saaras	Sarvam	`saaras:v4`	Supported Indian-language and Hindi-English calls; compare pauses and recognition hints.

Selection Rules

Rule	Effect
New cascaded agents prefer Soniox STT RT v5 with Deepgram Flux fallback.	Language compatibility can substitute a supported Deepgram model or disable fallback. Confirm the saved draft.
Flux can use English or multilingual Deepgram paths.	English agents use `flux-general-en`; supported non-English and mixed-language agents can use `flux-general-multi` with language hints where DialNexa can derive them.
Soniox uses valid language hints.	Hindi-English agents send separate `en` and `hi` hints to Soniox instead of an invalid combined code.
Soniox and Sarvam expose Response Eagerness.	The Speech Settings panel shows the patient-to-eager timing slider for supported paths.
Fallback STT must use a different selectable transcriber.	The current selector excludes AssemblyAI from primary and fallback choices, and the fallback selector also excludes the current primary transcriber.
Transcriber pricing can appear in the selector.	Workspaces using rate preview can see `₹x.xx/min` beside primary and fallback options. If a preview is unavailable, verify the separate plan-resolved fallback line item in Billing after a test call.
Call logs snapshot the model used.	Billing and debugging can refer to the exact transcriber model on the call.

Deepgram Language Compatibility

Model	Supported DialNexa language codes
Nova 3	`bn`, `en`, `gu`, `hi`, `hi-en`, `kn`, `mr`, `mul`, `ta`, `te`, `th`
Nova 2	`en`, `hi`, `hi-en`, `mul`, `th`
Flux	English and supported multilingual paths selected by the dashboard.

Malayalam (ml), Punjabi (pa), and Odia (od) do not use Nova 3. Odia also runs Soniox without language hints. If a saved combination becomes incompatible after a language change, choose a compatible transcriber before publishing.

Transcriber Fields

Field	Meaning
`id`	DialNexa transcriber id used by agent versions and billing lookup.
`provider`	Speech to text provider, such as Deepgram, Soniox, or Sarvam.
`model_id`	Provider model identifier such as `nova-3`, `nova-2`, `flux-general-en`, `flux-general-multi`, `stt-rt-v5`, or `saaras:v4`.
`name`	Human-readable name shown by the product, with dashboard display labels applied where helpful.
`description`	Provider model description.
`is_deleted`	Whether the transcriber is unavailable for new selection.

Which Transcriber Should I Start With?

Question	Start with
Is the caller mostly English?	Start with the saved Soniox primary and Flux fallback, then compare against Nova 3 if recognition evidence supports it.
Is turn-taking the main problem?	Deepgram Flux for a supported language, then compare against Nova 3 or Soniox.
Will callers mix Hindi and English?	Soniox with Hindi-English language setup.
Are post-call fields wrong?	Review transcript quality before changing extraction fields.
Are names or product words wrong?	Test provider, language, recording quality, and prompt examples.
Is primary STT sometimes slow?	Enable a compatible fallback STT and start with the `0 ms` default wait.

Speech To Text

Learn how transcribers affect live and post-call behavior.

Speech Settings

Tune Response Eagerness, Boosted Keywords, and Denoising Mode.

Latency And Turn Taking

Diagnose timing and interruption issues.

Provider Selection Guide

Choose the complete Voice AI stack.

​DialNexa Supported Transcriber Options

​Selection Rules

​Deepgram Language Compatibility

​Transcriber Fields

​Which Transcriber Should I Start With?

​Related Reading

Speech To Text

Speech Settings

Latency And Turn Taking

Provider Selection Guide

DialNexa Supported Transcriber Options

Selection Rules

Deepgram Language Compatibility

Transcriber Fields

Which Transcriber Should I Start With?

Related Reading