Customer success team offering voice support through an AI agent
Customers call and the AI employee handles the conversation naturally. No hold times, no scripts, just real dialogue.
Voice Calls
Voice Calls is a planned channel for speaking to an AI employee out loud and hearing it reply in real time, instead of typing. It is not available yet: there is no voice button in the workspace today, and the feature is paused while the underlying voice flow is redesigned. When it ships, a voice call will run through the same skills, tools, and memory as a typed conversation.
Sometimes typing is not the fastest way to communicate. Voice calling lets you speak to your employee the way you would talk to a colleague on the phone. It listens through real-time speech-to-text, understands the request, and responds with text-to-speech. The conversation feels natural, not like dictating to a machine.
Voice is not a stripped-down mode. Your employee has access to the same memory, skills, tools, and capabilities during a voice call as it does in chat. Ask it to "check my calendar and find a free slot next Tuesday," and it opens Google Calendar, scans your schedule, and reads back the available times. Ask it to "draft a follow-up email to the client from yesterday's meeting," and it writes the draft using context from the meeting notes you uploaded.
Voice calls are transcribed and stored in the conversation history. You can review what was said, search for specific topics, and reference past voice interactions the same way you reference past chat messages. Nothing is lost because you spoke instead of typed.
Where this stands today matters as much as the description. Voice is not switched on in the workspace right now: there is no voice button, and the channel is paused while the underlying voice flow is redesigned. It shows as coming soon rather than offering a control that would lead nowhere. What follows is the shape it takes when it returns, not something you can press today.
The design decision behind it is worth knowing, because it runs opposite to most voice assistants. A voice bot that answers in a fraction of a second is usually a thin model with no tools, no training, and no memory behind it. Sistava puts the whole employee in the middle of the call instead, so a turn takes a few seconds rather than a blink, and in exchange the thing you are talking to can open your calendar, read what you trained it on, and actually finish the task. It is closer to a short radio exchange with a colleague than to a phone menu.
Speech also starts before the answer is finished. As the employee writes its reply, each complete sentence is spoken the moment it is done rather than waiting for the whole response, so you hear the opening while the rest is still being worked out. The words are kept as text either way, which is why a conversation held entirely out loud still ends up searchable in the same history as everything you typed.
Talk to Your AI Employee Out Loud
Sistava supports full voice conversations with your AI employee. Speak naturally, and speech-to-text converts your words in real time, while the agent responds with natural text-to-speech audio. No typing required.
Voice conversations use the same underlying agent as chat, so every skill, tool, integration, and memory is available. Asking your AI employee to pull last week's sales report or draft a follow-up email works just as well by voice as it does in writing.
Same Capabilities, Different Interface
Voice is not a stripped-down version of the product. Your autonomous agent can execute multi-step tasks, use tools, and access integrations during a voice call, just as it does in chat. The interface changes; the intelligence does not.
This matters for hands-free workflows. A field technician, a manager in transit, or an executive between meetings can delegate complex tasks by speaking naturally, without opening a laptop or typing a prompt.
Built for Real Conversation, Not Voice Commands
Sistava voice is designed for back-and-forth dialogue, not single-sentence voice commands. You can ask a follow-up, change your request, add context, and the agent handles it all within the same voice session.
Conversations are automatically transcribed and logged, so nothing is lost after the call. You can review what was discussed, what the agent did, and any outputs it produced, all from the standard conversation history.
There are honest limits worth stating up front. A call runs for as long as the connection holds, so if your network drops the call ends rather than quietly reconnecting, and you pick up by starting again with the same employee, which still has the whole conversation behind it. Time spent talking is metered by the minute on top of the work the employee does during the call, so a long session draws more from your balance than a short one.
How It Works
Speak to your AI agent out loud and get spoken responses, with full access to all tools and memory.
Voice mode connects a speech-to-text engine on the input side and a text-to-speech engine on the output side, with the full agent in between. You speak, the agent listens, processes the request with all its tools and memory available, and speaks the response back. It is not a simplified voice assistant. It is the same capable agent you work with in chat, accessed through your voice.
Voice is useful for hands-free workflows, quick questions while working on something else, and situations where typing is inconvenient. The agent remembers everything said in a voice session the same way it remembers a text conversation. Switch from voice to chat mid-session and the context carries over completely. No need to re-explain what you were discussing.
There is a deliberate tradeoff in that design. Because the whole employee sits in the middle of the call, a turn takes a few seconds rather than being instant, and that is the price of talking to something that can genuinely use your tools and your training instead of only talking back. Each sentence is spoken as soon as it is finished, so the reply starts arriving in your ear while the rest of it is still being worked out.
Use Cases
Sales team qualifying leads through voice calls
The AI agent engages prospects in natural conversation, qualifies them, and hands off to a human when ready.
Operations team running verbal status checks with an AI employee
Talk to the agent out loud and get answers immediately. No keyboard, no screen, just a conversation.
Field team accessing an AI agent hands-free
Workers on the floor or in the field talk to their AI employee without stopping what they are doing.
Comparison
| Before | After |
|---|---|
| Interacting with AI requires typing, which is slow or impossible in some contexts. | Talk to your AI employee naturally, voice works wherever typing doesn't. |
| Voice interfaces feel rigid and menu-driven. | The AI agent holds a real conversation, not a scripted call flow. |
| Phone support requires human agents available around the clock. | An AI employee handles voice calls 24/7 with no staffing required. |
| Switching between typing and doing breaks focus. | Voice keeps you in your workflow while the AI agent handles the conversation. |
FAQ
Does voice support the same tools and integrations as chat?
Yes. Voice is a full interface to your AI employee, not a limited mode. The agent can use any tool it has access to, including web search, OAuth apps, and custom integrations, during a voice conversation.
Are voice conversations saved somewhere I can review later?
Yes. Every voice session is transcribed in real time and saved to the conversation history. You can read the full transcript, see every tool call, and review any outputs the agent produced.
How accurate is the speech-to-text transcription?
Transcription is powered by a high-accuracy STT engine tuned for business vocabulary. It handles natural speech patterns, partial sentences, and domain-specific terms well. You can also correct any misrecognized text in the transcript after the call.
Can I use voice on mobile?
Yes. The voice interface works on any device with a microphone through the Sistava web app. No separate app download is required.
Can my AI employee handle voice conversations, not just text chat?
Yes. Voice calls use speech-to-text and text-to-speech so your AI agent can speak and listen naturally. You can use voice alongside chat or as the primary interface.
Can I talk to my AI employee out loud today?
Not right now. Voice is a Sistava channel that is paused while the underlying voice flow is redesigned, so there is no voice button in the workspace today and it shows as coming soon. Web chat, Slack, Telegram, and each employee's own email address are all live in the meantime, and nothing you set up in those has to be redone when voice returns.
Do I need to install an app to use voice with my AI employee?
No. Voice is built to run inside the Sistava web app, using your browser and your device's microphone on a laptop or a phone, with no separate download and no desktop install. It cannot be switched on today, but when it returns there is nothing to install first.
Will a voice conversation show up in my written history?
Yes, that is the design. Speech is turned into text on the way in and the employee's reply is kept as text on the way out, so a spoken conversation lands in the same searchable history as everything you typed. You can reread it later and carry on in web chat without repeating what was said out loud.
I do my morning briefing by voice while making coffee. The agent gives me a rundown of overnight tasks, flags anything urgent, and schedules my priorities. It takes four minutes and I have not opened a dashboard to start my day in two months.
Where Voice Calls fits
Voice Calls is part of Ways you talk to them.
Chat in the app with live reasoning, speak to your AI voice agent over a call, message on Slack or WhatsApp, send an email, or embed a widget on your website. Every channel connects to the same AI agent with the same memory and capabilities. Switch channels mid-conversation and your employee picks up right where you left off.
- Ways you talk to them: Every channel. One conversation.
Read the guide
More in Channels
- Web Chat: Chat with any AI employee directly in the workspace, with a streaming reply, a live execution timeline showing what it is reading, thinking, and doing, and inline approve/reject buttons when it needs a sensitive action confirmed. It is the default channel: nothing to configure, works on desktop or mobile, and every conversation persists so you can pick it back up later.
- Connect an Email Provider: Point your own SendGrid, Mailgun, or Postmark inbound-parse webhook at a tenant-scoped endpoint and every email that lands there gets turned into work for an employee. Forward support requests, sales inquiries, or internal approval emails and the employee reads the sender, subject, and body, then acts on it in the background. You get a 202 response immediately; there's no waiting on the request.
- Personal Mailbox: Every employee gets its own email address on the shared Sistava domain the moment you hire it, no setup. Email it directly, CC it on a thread with other people, or forward something over, and it reads and replies within seconds. Free to send from, with a monthly cap by plan. Control the shared employee signature in Company Profile, or connect your own Gmail or Outlook when you want it sending as you, with no cap.
- Send from Gmail or Outlook: The built-in employee address is free and always on, but it sends as the employee, not as you. Connect your own Gmail or Outlook instead and an employee sends and replies from your real address, in your name, with no monthly sending cap on any plan.
- Talk to Your Employee on Video: In-App Video is a planned channel for live, face to face video calls with an AI employee, camera and microphone, directly inside the workspace. It has no working implementation today: it appears in Settings > Technical > Channels as a Coming soon placeholder only. Once it ships, it is meant to run on the same execution pipeline as every other channel, so the employee keeps its skills, tools, training, and conversation memory on a video call. If you need an employee in a live call today, it can already join a Google Meet, Zoom, or Microsoft Teams meeting as a participant, which is a different capability and available now.
- Chat Widget: The Chat Widget will let you embed an AI employee directly on your public website so visitors can ask questions and get answers without leaving the page. It is on the roadmap and is not available to configure yet: today it appears in Settings > Technical > Channels as a Coming soon placeholder with no setup, embed snippet, or Manage action.
- SMS: SMS is a planned channel for reaching an AI employee by ordinary text message, with no app to install. It is on the roadmap and not available today: there is no SMS number, no inbound texting, and no way to turn it on yet. Until it ships, use web chat or Telegram for mobile access from any phone.
- WhatsApp: WhatsApp is a planned messaging channel for talking with an AI employee from your phone. It is not connected yet: the card shows as coming soon and cannot be set up today. When it ships, it will carry the same employee memory, skills, and guardrails as web chat, Telegram, Slack, and the mailbox. Telegram and Slack are live now and give you the same access from a phone, so nothing you set up today has to be rebuilt when WhatsApp arrives.
- Discord: Discord is a planned channel for bringing an AI employee into the servers and direct messages your community already uses. It will connect the same way Slack does today: authorize a bot through OAuth, then map it to one employee. It is not available to connect yet, so no Discord traffic reaches an employee until it ships. Slack, Telegram, each employee's own email address, and web chat cover the same job in the meantime.
- Calendar Invites: Add your employee's personal address as a guest on any Google, Outlook, or Apple calendar event and they show up for the meeting automatically, no RSVP or extra app on your side. Once the meeting starts, the employee joins the Meet, Zoom, or Teams call, listens, speaks when addressed, and writes a summary afterward. There is nothing to switch on for the invite itself, just turn on the Meeting Attender tool for that employee once.
- Slack Channel: Bring your AI employee into Slack as a real bot user your team can mention, DM, or trigger with a slash command. Every reply lands in the same thread, and memory, tasks, skills, and tools stay shared with web chat, so a conversation started on Slack continues anywhere else. You approve or reject requests right from Slack, and the bot only speaks when mentioned, DM'd, or already in a thread.
- Telegram Channel: Connect an AI employee to its own Telegram bot so you can message it from your phone the same way you message a person. It answers direct messages instantly, and joins group chats where it replies only when mentioned or replied to. Memory, tasks, and tools are shared with the web app, so a conversation started on Telegram picks up right where it left off on the desktop, and back again.