DialNexa Speech Settings

Tune DialNexa speech settings for Response Eagerness, Audio Cache, Denoising Mode, Hinglish Map, transcriber behavior, and voice latency.

DialNexa Speech Settings control how an agent listens and speaks during a live call. The visible controls are intentionally focused: Response Eagerness for supported Soniox paths, Audio Cache for repeated speech, Denoising Mode for noisy audio, and Hinglish Map for Hindi-English wording.

Speech settings are where milliseconds, noise, and phrasing argue quietly. Let them argue in test calls, not during your biggest campaign.

Visible Controls

Control	When it appears	What it changes
Response Eagerness	When the selected transcriber is Soniox.	How patient or eager the agent is before replying to caller speech.
Audio Cache	Speech Settings for the agent version.	Whether repeated synthesized audio can be reused for faster playback.
Denoising Mode	Speech Settings for the agent version.	Whether background noise cleanup is applied.
Hinglish Map	When the selected language is Hindi-English.	Formal Hindi word substitutions used to make Hindi-English calls sound more natural.

Response Eagerness

Response Eagerness runs from patient to eager. It is not a quality slider. It is a timing choice.

Direction	Caller experience	Use when
More patient	Agent waits longer before responding.	Callers pause, think aloud, speak in longer sentences, or switch between Hindi and English.
More eager	Agent replies sooner after shorter pauses.	Callers answer briefly and the script benefits from quick back-and-forth.

If the agent interrupts callers, do not raise LLM temperature and hope for manners. Check transcript boundaries, greeting length, and Response Eagerness first.

Audio Cache

Audio Cache helps repeated text-to-speech output start faster. DialNexa tracks cache lookups, hits, misses, and new cache entries in call evidence when data is available.

Good candidate	Why it works
Fixed welcome message.	Same text and same voice configuration repeat.
Compliance disclosure.	Usually identical across many calls.
Short confirmation line.	Repeats often and is heard immediately by callers.

Poor candidate	Why it misses
Hi {{first_name}}, your payment is {{amount}}.	Variables change the generated text.
Long model-generated replies.	The model can say the same idea with different wording.
Fresh external API responses.	Data changes from call to call.

Denoising Mode

Denoising Mode can help with background noise, but it should be tested with the actual phone path. Noise cleanup can improve recognition, but aggressive cleanup can also damage speech details.

1. Listen to the bad call

   Open Call History, play the recording, and identify noise, echo, clipping, silence, or distance from microphone.

2. Change only Denoising Mode

   Keep transcriber, voice, prompt, and phone route the same for the next test.

3. Retest the same call pattern

   Use the same caller, route, and script if possible.

4. Compare transcript and recording

   Keep denoising only if it improves recognition without making speech sound unnatural.

Hinglish Map

Hinglish Map appears for Hindi-English setup. Use it when the agent uses formal Hindi words that callers would not use in a real conversation.

Add a mapping when	Avoid mapping when
Callers consistently use a simpler mixed-language phrase.	The original term is required for legal, medical, or compliance precision.
The replacement is shorter and easier to understand over the phone.	The replacement could confuse post-call reporting.
You verified the phrase in recordings or real user language.	You are guessing from written Hindi without listening to calls.

Troubleshoot By Symptom

Agent replies before the caller finishes

Use a more patient Response Eagerness setting where available, shorten the welcome message, and inspect live transcript boundaries.

Repeated lines are still slow

Check whether the text repeats exactly. Names, amounts, dates, and model rewording create new phrases.

Noisy calls produce bad transcripts

Compare recording and transcript, try Denoising Mode, then compare transcribers through the same route.

Hindi-English sounds too formal

Use Hinglish Map, add prompt examples, and test the selected voice on mixed-language phrases.

Related Reading

Speech To Text

Understand transcribers and transcript evidence.

Text To Speech

Tune voices and Audio Cache.

Latency And Turn Taking

Diagnose response timing.

Audio Cache Monitoring

Read cache metrics after calls.