Speech To Text And Transcription In DialNexa

Compare DialNexa speech to text providers for realtime transcription, language support, response timing, transcript accuracy, and cost.

Speech to text in DialNexa is the part of a Voice AI call that decides what the system believes the caller said. If this layer is wrong, every downstream feature inherits the mistake: the model answers the wrong question, functions receive wrong arguments, summaries sound confident but false, and post-call fields become review work.

If the transcript says the caller asked about carrots when they clearly asked about careers, do not rewrite the whole prompt yet. Start with listening.

DialNexa Speech To Text And Transcription Options

Display name	Provider	Best fit	Important limit
Deepgram Flux	Deepgram flux-general-en for English, or flux-general-multi for supported non-English and mixed-language calls.	Fast turn boundaries, English calls, and supported Hindi or Hinglish tests where Flux is enabled.	Test real caller audio. Multilingual Flux uses language hints where DialNexa can derive them, and broad multilingual choices may run auto-detect.
Soniox	Soniox stt-rt-v5	Hindi-English, Hinglish, multilingual, and Indian-accented calls.	Test noisy phone calls and local names before scaling.

The selector can show different options depending on the agent language. Pricing per minute for each option is shown next to the selector in the dashboard. Cascaded agents can also use fallback STT from the transcriber settings popover. The current dashboard selector does not expose AssemblyAI for new primary or fallback choices.

For help comparing transcription providers, see the voice AI provider selection guide. For how transcription evidence appears after the call, see transcripts, recordings, and summaries.

Deepgram Flux Versus Soniox

Use Deepgram Flux

Start with Deepgram Flux for English calls where fast turn boundaries matter. For supported non-English or mixed-language tests, DialNexa can use multilingual Flux with language hints derived from the agent language.

Use Soniox

Use Soniox when callers naturally mix Hindi and English, speak in Indian regional accents, or when Deepgram produces high error rates for your caller base. DialNexa sends English and Hindi language hints to Soniox, and the Speech Settings panel exposes Response Eagerness for supported Soniox paths.

What DialNexa Configures Behind The Selector

These details explain the behavior users see in the dashboard and call records.

DialNexa behavior	User-visible result
Deepgram Flux uses short endpointing for English.	English calls feel quicker because the system closes caller turns sooner.
Deepgram Flux can use the multilingual model for supported non-English languages.	A Hindi or Hindi-English agent can run through flux-general-multi with language hints such as hi and en when DialNexa can derive them.
Soniox uses STT RT v5 and receives valid language hints.	Supported single-language agents send that language’s ISO hint in strict mode. Hindi-English calls send en and hi hints so mixed-language speech is treated as code-switched speech rather than one textbook language. Unsupported or broad language choices run without strict hints.
Soniox endpoint detection is enabled.	Soniox can finalize caller turns without an extra post-final hold, which can reduce response latency on supported calls.
Soniox controls Response Eagerness.	The patient-to-eager slider appears only for supported Soniox paths.
Boosted Keywords are sent through the selected provider’s supported path.	Deepgram Nova 3 and Flux receive keyterm hints, older Deepgram keyword paths receive keyword hints, and Soniox receives context terms.
Provider errors are handled during runtime.	Temporary connection drops, malformed frames, or provider restarts can be dropped, retried, or recovered instead of immediately ending the call.
Fallback STT runs a backup transcriber in parallel.	Users can choose a different fallback transcriber and a fallback wait time in milliseconds. A valid fallback final result is processed once when it wins the timing race.
Transcriber pricing is fetched per selected option.	Users can see INR per minute beside primary transcriber rows when the billing preview is available. Fallback choices currently show ₹0.00/min.

Boosted Keywords For Speech To Text

Boosted Keywords are recognition hints for supported cascaded transcribers. Add short terms that the caller is likely to say and that the transcriber might otherwise miss.

Use Boosted Keywords for	Avoid using them for
Brand names, product names, people names, localities, acronyms, and uncommon phrases.	Long instructions, whole scripts, punctuation-heavy text, or terms the caller will never say.
Terms that appear in recordings but are misheard in transcripts.	Guessing before you have call evidence.
Small, reviewed lists that match the campaign or use case.	Large glossaries that make the hint list noisy.

The Speech Settings panel validates Boosted Keywords before saving. Terms can contain letters, numbers, and spaces only. DialNexa preserves multi-word phrases, removes duplicate terms case-insensitively, and sends the resulting list to Deepgram or Soniox when the selected transcriber supports it.

Fallback STT

Fallback STT helps when the primary transcriber is slow or unreliable for a specific caller population. When enabled, DialNexa can use a backup transcriber if it finalizes first and the primary result does not arrive within the configured wait.

Setting	Recommendation
Primary transcriber	Keep this as your best-fit provider for the caller language.
Fallback transcriber	Pick a different provider or model from the primary option.
Fallback wait	Start with 500 ms, then tune from real call recordings and transcripts.

Fallback STT applies to cascaded agents. Speech to Speech agents do not use a separate STT provider.

The fallback transcriber must have a different transcriber ID from the primary transcriber. The dashboard hides the primary option from the fallback list. Create or update API requests that send the same ID for both return 400 Bad Request.

The current fallback selector displays ₹0.00/min. After a test call, review Billing transactions for a separate fallback-transcriber component because the final line item is resolved from the workspace billing plan.

DialNexa processes a valid fallback final result only once. If the fallback result is queued again during timing coordination, it is not dropped just because the first pass was deferred.

Transcript Types

DialNexa can show more than one transcript view for the same call.

Transcript	When to use it
Live transcript	Debug turn-taking, interruptions, and what the agent heard before replying.
Accurate transcript	Review cleaner post-call text when available.
Recording	Settle disputes about what was said, noise, overlap, silence, pronunciation, and phone quality.

Text tells you what the system believed. Audio tells you what happened. When they disagree, trust the recording first.

How To Test Speech To Text

1. Use the same caller script

   Compare transcribers with the same greeting, caller answers, interruption, name, city, number, and final outcome.

2. Test names and places

   Use real customer names, locality names, company names, product terms, and common abbreviations.

3. Test interruptions

   Ask a caller to speak during the greeting, correct themselves mid-answer, pause, and give one-word replies.

4. Test language switching

   For Hindi-English calls, include English numbers, Hindi phrases, and mixed casual replies in the same call.

5. Compare transcript with recording

   Mark the exact point where the transcript diverges from audio.

6. Review downstream effects

   Check function arguments, workflow branches, summaries, and post-call fields. Bad listening quietly becomes bad automation.

How Transcription Affects Integrations

Integrations usually receive data that started as caller speech. If the transcript is wrong, a CRM update, ticket note, WhatsApp message, or spreadsheet row can be wrong too.

Integration result	Transcription risk	What to inspect first
CRM field update in HubSpot or Salesforce.	Name, company, lead score, or intent was misheard.	Recording plus accurate transcript.
Ticket note in Zendesk or Intercom.	Issue category or callback detail was captured incorrectly.	Transcript segment near the caller’s problem statement.
WhatsApp or email follow-up.	The agent repeats the wrong date, amount, or next step.	Post-call fields and the exact generated message.
Review queue in Google Sheets.	Bad extraction looks like a bad lead record.	Transcript, summary, and field definitions together.

Common Speech To Text Mistakes

Assuming one transcriber fits every language

Deepgram Flux and Soniox can both be useful, but they behave differently by language, accent, and noise. Compare them on real calls before standardizing a stack.

Passing invalid language hints to Soniox

The runtime filters language hints to valid Soniox values. For Hindi-English agents, DialNexa sends English and Hindi hints rather than an invalid combined language code. For unsupported broad choices, it avoids strict hints instead of sending a value Soniox cannot use.

Treating Boosted Keywords as a transcript guarantee

Boosted Keywords bias recognition toward important terms. They do not force exact output, so recordings and transcript review are still required.

Changing the model before checking the transcript

If the LLM received the wrong caller words, the LLM is not the first problem.

Ignoring the phone path

Plivo, SIP trunking, and web calls can produce different audio with the same agent. Compare through the same route when testing transcribers.

Testing only quiet calls

Real callers use speaker mode, traffic, low signal, and short answers. Test those before a large campaign does it for you.

Recap

Choose a transcriber using real caller language, accents, noise, and timing requirements. Compare transcript accuracy and response behavior with the same test calls before publishing the selected stack.

Related Reading

Supported Transcribers

Read the reference table for selectable transcribers.

Speech Settings

Tune Response Eagerness and Denoising Mode.

Latency And Turn Taking

Understand how turn boundaries affect response timing.

Transcripts And Recordings

Review call evidence after live calls.