Vokeva AI — Dashboard

Your agents

~$0.05 / min

Includes AI · Voice synthesis · Transcription

~490ms

Agent name

Agent type

AI model

Choose a model

Who speaks first?

Response length

Opening greeting

What the agent says at the start of every conversation

Agent instructions

Tell the agent who it is, how it should behave, and what it knows

Creativity: 0.7

FocusedCreative

Max response length (tokens): 500

Limits how long each AI response can be. Lower = more concise.

Knowledge base

Paste any content directly — FAQs, product info, scripts

0 characters

Free — no storage cost

Drop files here or click to upload

PDF, DOCX, TXT, CSV — max 10MB each

$0.10 per document/month storage

Auto-fetch pricing

Manual fetch: Free

Daily auto-fetch: ~$0.001/day

Weekly auto-fetch: ~$0.007/month

Monthly auto-fetch: ~$0.001/month

Cost covers server processing to fetch and index page content. Set frequency per URL after fetching.

Knowledge base cost: $0.00/month (text only — free)

Cost breakdown for this agent

STT (Speech-to-Text)Standard STT · ~$0.006/min

TTS (Text-to-Speech)TTS · ~$0.015/min

AI ModelGPT-4o Mini · ~$0.001/min

Base cost~$0.022/min

Platform services hosting, routing & monitoring~$0.009/min

Total~$0.031/min

Agent voice

Language

All voices support 40+ languages. Select your language and the voice will automatically respond in it.

Choose a voice

Speaking pace: 1.0x

Slow (0.5x)Fast (2.0x)

Adjust how fast or slow the voice speaks

Phone number

Assign a Twilio phone number to this agent for inbound/outbound calls

Speech recognition

Recommended

Deepgram Nova-3

$0.0049/min

Latest, most accurate for voice agents

Pro

Deepgram Flux

$0.0059/min

Built-in turn detection, lowest latency

Deepgram Nova-2

$0.0043/min

Fast and reliable, previous generation

OpenAI Whisper

$0.006/min

Great for accented speech

Google Speech

$0.016/min

Best for non-English languages

Enable fallback transcriber

Minimum confidence level: 0.0

Accept allHigh confidence only

Transcripts below this confidence score are ignored

Important keywords

Help the AI recognise these words accurately (product names, technical terms). Comma-separated.

How the agent listens

Response delay: 0.4s

Instant2 seconds

How long the agent waits after you finish speaking before replying

Words before interrupting: 3

Instant10 words

Customer must speak this many words before the agent stops talking

Interrupt threshold: 0.4s

0.1s1s

Agent stops speaking after customer talks for this long

Recovery time: 1s

0s5s

Time before the agent speaks again after being interrupted

Silence before responding: 1.5s

0.5s10s

How long to wait after speech ends before agent responds

Voicemail

Leave a voicemail if no answer

Escalation to human

Transfer to a human when the agent can't help

📊 Widget Activity

Active visitors

0

Chats today

0

Callbacks today

0

Bookings today

0

🔧 Installation

Paste this snippet anywhere on your website. Works with all platforms including WPCode, Google Tag Manager, and any tag manager. The widget auto-detects logged-in users, fetches all settings from the server, and just works.

Where to paste

WordPress (WPCode): WPCode → Add Snippet → HTML Snippet → Footer

WordPress (theme): Appearance → Theme Editor → header.php → before </head>

Shopify: Online Store → Themes → Edit code → theme.liquid → before </body>

Google Tag Manager: Custom HTML tag → Fire on All Pages

Wix: Settings → Custom Code → Add code → Body end

Squarespace: Settings → Advanced → Code Injection → Footer

Webflow: Project Settings → Custom Code → Footer Code

React/Next.js: Add to _document.js or layout.tsx <head>

🎨 Appearance

Widget color

Widget position

Custom title

Shown in the widget header. Leave blank for agent name.

Chat greeting

⚙ Features & Behaviour

Auto-open delay (seconds)

0 = disabled. Widget auto-opens after this many seconds.

Excluded pages

Comma-separated URL paths where the widget should NOT appear.

Offline message

Shown when outside callback hours. Leave blank to disable.

User identification

The widget auto-detects logged-in users by scanning cookies, localStorage, meta tags, WordPress DOM, and common window objects.

Auto-detect works on most sites. Use meta/window if you need explicit control.

🤖 Feature Toggles

Show on mobile

Display widget on mobile devices

AI quick replies

AI suggests contextual reply buttons

Show branding

Display "Powered by Vokeva" in widget

Human takeover

Take over chats from Live page

Voice calls

Browser-based voice calls in widget

AI callback

Visitors request phone callbacks

👤

Pre-chat Form

Collect visitor info before the first message. Visitors who provide their name will be identified in the Live page and Chat Logs.

Ask for name

Required before chatting

Ask for email

Optional field

Built-in actions

Transfer call to a human

Automatically end call when done

Allow keypad input during call

Let callers press keypad digits during a conversation (e.g. press 1 for sales). Configure in Call Behavior tab.

Send SMS summary after call

Custom webhooks

Webhooks notify your systems when events happen

Humanoid AI layers — active on all calls

✓Layer 2 — Adaptive follow-ups

✓Layer 3 — Natural speech patterns

✓Layer 4 — Emotional intelligence

✓Layer 5 — Ultra-low latency TTS (Cartesia)

✓Layer 6 — Prosodic mirroring

✓Layer 7 — Backchanneling (mm-hmm, I see...)

✓Layer 8 — Session topic memory

○Layer 9 — Prosodic mirroring v2 (coming soon)

These layers run automatically on every call. No configuration needed.

What to track from every conversation

Call summary

Auto-generate summary after each call

Summary style

Success tracking

What makes a call successful?

Examples: "Customer issue was resolved" / "Appointment was booked" / "Customer expressed satisfaction"

—

Success rate

Connect analytics to see success rate

Alerts

Notify me when a call fails

Notify me when sentiment is very negative

Notify me when call exceeds 10 minutes

Notification channel

Call limits

End call after silence: 30s

10s120s

Hang up if nobody speaks for this long

Maximum call duration: 10 min

1 min60 min

Automatically end the call after this time

Privacy

Record calls Store transcripts

Keypad input (IVR)

Accept keypad button presses

Silence filler messages

Messages the agent says when the caller goes silent

Max silence prompts: 3

How many times to prompt before ending the call

Silence before prompt: 10s

5s60s

Seconds of silence before saying a filler message

Call ending

Goodbye message

What the agent says just before ending a call

Voicemail detection method

Off AI-powered Uses AI to detect voicemail — most accurate Standard detection Faster, less accurate

Presets

Optimised for long-form agents: long silence tolerance, 20-min calls, patient turn-taking

Proactive Triggers

Auto-engage visitors based on their behavior. Triggers fire once per session by default.

Appointment Booking

Enable booking

Available days

Slot duration

Start hour

End hour

Timezone

Confirmation message

Upcoming Bookings

No bookings yet.

Agent Persona

Agent Name (leave blank to disable persona)

Personality Style

Advanced Mode

Enables advanced behaviours (sentiment tracking, follow-ups, strict endpointing)

Turn Detection Mode

Controls when AI responds after user pauses

Thinking Sounds

Plays brief fillers like "Mm." or "I see." while AI generates a response — eliminates dead silence

Enable thinking sounds

Trigger chance: 40%

0%100%

Filler phrases (comma-separated)

Conversation Style

Natural acknowledgments

Starts each response with brief acknowledgment ("That makes sense." / "I see.")

Variable response length

Short questions after strong answers, scaffolded questions after weak ones

Emotional intelligence

Adapts tone when nervous (softer) or confident (sharper follow-ups)

Adaptive speaking pace

Mirrors the user's speaking speed — slow speakers get slower responses

Graceful interruption

"Go ahead." when user interrupts mid-speech

Breath pauses

Natural 120ms pause between sentences for realistic rhythm

Intelligence

Conversation memory

References past mentions naturally ("Earlier you mentioned...")

Pronunciation boost

Improves recognition of names/companies from context

Smart silence handling

"Take your time" on long pauses instead of interrupting

Thinking pause threshold: 4000ms

2s10s

Human Transfer

Enable human transfer

Transfers to a real person when user says "speak to a human"

Transfer Message

Transfer Webhook URL (receives POST on transfer)

Session Room Defaults

Default UI settings for the browser session room. Users can still toggle these during the call.

Subtitles are always enabled. Ambient sound has been removed from the session room.

Voice Cloning COMING SOON

Upload a voice sample to clone a custom AI voice. Powered by ElevenLabs voice cloning API.

Language

Agent Language

Affects both speech recognition (STT) and voice output (TTS)

Call logs

Call ID	Assistant	Type	Status	Sentiment	Score	Start Time	Duration	Cost

Chat History

Loading chats...

Select a conversation to view

Phone Numbers

Connect your Twilio account

Twilio Account SID

Twilio Auth Token

Phone Number

Must be a number you own in this Twilio account

Setup guide

1. Get your credentials at twilio.com/console → Account Info

2. Buy a number at twilio.com/console → Phone Numbers → ~$1.15/month

3. No Twilio account? Sign up free at twilio.com

Your credentials are stored securely and used only for your agents' calls.

API keys

API keys let external systems interact with your agents.

Coming soon

Billing

Current plan

Free

Minutes used

0 / 100

Active agents

0

Upgrade your plan

Starter

$29/mo

3 agents
500 minutes/month
Phone support

Pro

$99/mo

10 agents
2,000 minutes/month
Priority support
Analytics

Agency

$299/mo

Unlimited agents
Unlimited minutes
White-label
Custom domain

White Label Settings

Brand your platform

Company name

Custom domain

Point a CNAME record to vokeva-backend.onrender.com

Logo URL

Brand color

Sub-accounts (clients)

Email

Name

Plan

Agents

Your agents

AI model

Knowledge base

Cost breakdown for this agent

Agent voice

Speech recognition

How the agent listens

Voicemail

Escalation to human

📊 Widget Activity

🔧 Installation

🎨 Appearance

⚙ Features & Behaviour

🤖 Feature Toggles

Pre-chat Form

Built-in actions

Custom webhooks

What to track from every conversation

Call summary

Success tracking

Alerts

Call limits

Privacy

Keypad input (IVR)

Silence filler messages

Call ending

Voicemail detection method

Presets

Proactive Triggers

Appointment Booking

Upcoming Bookings

Agent Persona

Thinking Sounds

Conversation Style

Intelligence

Human Transfer

Session Room Defaults

Voice Cloning COMING SOON

Language

Call logs

Call Detail

Chat History

Phone Numbers

API keys

Billing

Upgrade your plan

White Label Settings

Brand your platform

Sub-accounts (clients)

A/B Tests

Variants