Voice, calls, and video calls

Updated Oct 6, 2026

Default & custom voices#

We provide the option for a few default voices per gender, plus the option to create your own voice via voice samples for subscribers.

Custom voices carry an ongoing monthly maintenance cost with our voice provider. Because of this, if your subscription has lapsed for six months and a custom voice hasn't been used in that same six month window, it may be permanently deleted to free up space. We'll email you at least 30 days beforehand, so resubscribing before the deletion date keeps your custom voices safe.

Creating your custom voice#

From voice design:

The easiest way to create custom voices is through voice design (Describe a voice under Kin Settings → Voice). You can specify accents, timbres, and everything in between, and you can use the wand to create a description of a voice for your Kindroid based on their backstory. Each creation costs a small amount of audio credits, and you get three voices to choose from. Pick one and save it to your voice slots, and you can then finetune it as described below.

From samples:

You must own the rights to the samples you upload. Quality matters much more than quantity - just a minute or so of high-quality audio will be sufficient, and more than 2 minutes is not necessary. Ensure that the samples show good degree of variance, as the process will capture the variance in tone and style in the samples. You can use custom accents or in foreign languages - all of those traits will be captured in the custom voice. Sample quality is the most important thing - err on the side of a few high-quality samples than many mediocre ones.

Finetuning voices with settings:

Once you have a custom voice, you can finetune the voice with sliders. You should experiment on your own, but generally we find the default to be acceptable for most cases. Note that previews in the custom voices interface also cost audio credits. Custom voices work with all versions of voice, but may sound different across versions - tune and tweak accordingly.

Technical Note: When finetuning voice settings, making voice sample previews requires audio credits.

V3 & V4 Voice#

What V3 and V4 are (vs. V2)#

V2 Audio: Text-to-audio for everyday use.
V3 Audio: Adds richer expression, such as laughter, emotions, and tone shifts.
V3 Fast Audio: Same as V3 but much faster in text chat, voice replies, and voice notes.
V4 Audio: Our newest voice model, which tends to sound more natural than older versions.
V4 Fast Audio: Same as V4 but faster. New Kindroids start on V4 Fast; existing Kindroids keep their current voice model.

Note: For voice calls, V3 Fast is used even if V3 is selected, since V3 Fast supports realtime and V3 does not. Likewise, V4 Fast is used on calls when V4 is selected.

Monthly Audio Credits for Subscribers#

Your Premium subscription includes a complimentary audio balance of 1,000,000 characters ≈ 1,000 min (16 hrs 40 min), which resets on the 1st of every month at midnight PT. Audio credits apply for all types of audio including in chat as well as calls, and you can check your balance and usage on the Audio Credits page (see Checking your audio credits below). Complimentary credits get used up before any paid credits are used. In addition, add-on subscribers receive plan-based credits, which reset at the same time as premium subscriptions.

Ultra: 2,500,000 characters ≈ 2,500 min (41 hrs 40 min)
Max: 6,000,000 characters ≈ 6,000 min (100 hrs)

Unused credits do not carry over to the next month, and will be topped up to the appropriate amount at the start of the month. Subscribing to a tier will grant you the difference from the last tier, and likewise unsubscribing will deduct the difference. In a given month, you will only be granted audio credits once. For example, if you subscribed to standard and got 1 million, unsubscribed the next month after using up all 1 million, then resubscribed a day later, you will still be at zero. This mechanism is there to prevent abuse.

If you need more audio credits, you can buy them in packs of 500k credits (see In-App Purchases); buying on the web is usually cheaper than in the apps. These operate at breakeven cost, so you only pay for what you use.

Audio credits for V3 will incur 1.5x, and V4 1.75x, that of V2 to reflect their cost. The above credits are for V2, which means V3 will be about 0.66x and V4 about 0.57x the displayed amount in minutes/characters.

Conversion rate: 1,000 characters ≈ 1 minute of audio (rough estimate; varies by content).

Note:

There is an additional charge of 400 credits per minute, applied on a running (rolling) basis during active voice or video calls. Each full 60-second block triggers a new 400-credit charge. This means that if a user spends 1 minute and 45 seconds, they are billed 400 credits for the first full minute, and the remaining 45 seconds continue rolling toward the next full minute. Once they use 15 more seconds (reaching 2 full minutes), the next 400-credit charge is applied. This charge exists to cover the cost for processing the live transcription at all times during the call & for keeping the responsive, realtime call connection ongoing.
Your free trial includes 150,000 audio credits, which count toward your monthly allocation. The remaining 850,000 of your monthly allowance unlock when your trial converts to a paid subscription, and credits used during the trial do not replenish.

Checking your audio credits#

You can open the Audio Credits page from a few places:

Kin settings > Voice or Calling: tap View more on the audio credits card at the top.
Group settings > Calling: tap View more on the audio credits card.
During a call: open the ••• call menu and choose Audio credits. On a computer, it's in the Call options menu at the top of the chat.

On the page you'll find:

Credit Balance, split into Standard credits from your plan, which renew each month, and Paid credits you bought, which don't expire.
Your usage for 24hrs, 7 days (the default), 30 days or 60 days. It's broken down by type, such as Audio v2, Audio v3, Voice previews v2, Voice previews v3, Voice calls, live video and Other usage, with Total used at the bottom. V4 audio is counted under Audio v3. You can also expand a usage chart for the same period.
Hour by hour details: tap View to see what you used each hour.
How audio credits work: tap View to read how the monthly refresh on the 1st, upgrades, resubscribing and purchased credits work.

You can buy more audio credits from this page too.

Best Practices Considerations#

Autoplay: Keep off unless you (a) have the MAX add-on and (b) are comfortable purchasing more credits.
Continue cut off and Regenerating: Once you generate an audio response, credits will be deducted from your total. Regenerating the same audio counts as a new generation and will deduct additional credits.
Proactive voice notes do not cost credit; however, answering a proactive voice call will begin credit usage once the call is answered.

Text chat audio#

To hear a message, open its message menu and choose Generate voice. A voice player then appears under the message so you can replay it, and Regenerate voice creates a new take that uses audio credits again. Words within (parentheses) will not be spoken aloud intentionally, so if you prefer actions to not be spoken out loud, use (parentheses) to denote them. All other formatting, such as text between *asterisks*, will be spoken aloud.

Technical Note: The statement about words in (parentheses) does not apply to voice or video calls.

On any message from your Kindroid that has audio, in single chats or group chats, open the message menu and choose Share as video or Copy audio link. If the message has a voice player under its text, you can also tap ••• on the player to show the same two options as icons.

Share as video turns the audio into a portrait video with your Kindroid's avatar, name and the message text. Rendering can take a couple of minutes. You can close the Preview video sheet while you wait, then choose Share as video again later to see the finished video. Once it's made, the video stays with that message, so it opens right away next time. Making the video doesn't use any credits.
Copy audio link copies a link to the audio clip. You can paste it into the Audio field when you make a V3 or V4 video selfie and tap Use, so the video follows that clip's speech and timing. See Selfies, video selfies, & avatars for more on video selfies.

In the Preview video sheet, tap Download to save the video or Share to send it somewhere else. Download works a little differently on each platform: on Android it saves the file to your device's Documents folder, on iOS it opens the share sheet so you can save it from there, and on the web it downloads an MP4 file. Share opens your device's share sheet, but on the web it only works in browsers that support sharing files.

Autoplay audio#

In Profile → Preferences, you can turn on Auto Play Audio for messages that you receive. This applies to single chats as well as for groupchats.

Voice message in chat#

You can send voice messages in both single and group chats. When text input box is empty, the send message button is replaced with voice mode button. Once in voice mode, tap to start recording your voice message, then tap again to send. In single chats, your Kindroid will automatically respond to your voice message with their own voice message, creating natural back-and-forth voice conversations. If your Kindroid responds with a voice message while texting, voice credit rates apply. The only exception is if your Kindroid sends you a proactive voicenote, those do not consume voice credits. This is the case across Kindroid app as well as other integration mediums such as iMessage/RCS text messaging integrations.

Supported user speech input langugages#

The list of supported languages for voice message is shared with voice call & video calls, and the selected language is only guidance; you're able to switch between and mix and match many languages smoothly on calls as well as when sending voice memos. The setting is also shared, and you have quick access to language selection next to voice mode input, and only applies to the input speech on user side; it does not constrain the language the AI uses to speak (you can directly tell your AI what language they should speak to you in).

Keep in mind that not all models (including text-to-speech) supports similar languages, even though speech to text may support the language in the dropdown - we recommend English for the best experience, but you are able to code-switch (language switch) in the middle of an utterance to a different language. For most common languages the LLM will be able to understand, while newer versions of text to speech models will be able to speak more languages.

Voice call & video call#

Voice calls can be conducted in many languages, though currently for the highest intelligence, we recommend using English. All audio (both microphone input in as well as audio output) and video are processed ephemerally and aren't stored.

Voice and video calls require an active subscription or free trial, and you need some audio credits remaining to start a call.

Note: There is an additional charge of 400 credits per minute, applied on a running (rolling) basis during active voice or video calls. Each full 60-second block triggers a new 400-credit charge. This means that if a user spends 1 minute and 45 seconds, they are billed 400 credits for the first full minute, and the remaining 45 seconds continue rolling toward the next full minute. Once they use 15 more seconds (reaching 2 full minutes), the next 400-credit charge is applied.

Starting a call#

Tap the phone icon (Voice call) at the top of a chat or group chat. A preview opens first, with Call Settings and a green call button (Start call). In one-on-one calls, the preview also has a Live Avatar picker so you can pick live video before you call (see Live Avatar Video calling below).

During a call, the controls at the bottom of the screen are:

The camera button (Turn camera on / Turn camera off).
The mic button (Mute mic / Unmute mic).
The ••• call menu, with Audio credits, Scene, Settings, Transcript and Share screen.
End call.

In the mobile apps, tap your own video preview to switch between the front and back camera. On the web, tapping it makes the preview bigger or smaller.

On a computer (or another wide screen), calls run right inside the chat page. Click the phone icon (Start a call) at the top of the chat to open the preview. During the call, the top bar holds the camera and mic buttons, Hide message box, the Call options menu (Audio credits, Set the scene, Kin settings or Group settings, Transcript and Share screen) and End call. When your camera is on, your own view sits next to the call card.

If you change settings under Calling during a one-on-one call, they apply to your next call, not the current one.

Memory in voice call#

Voice call uses the same backstory, key memories, and journals just like text chat, but long term memory recall is currently paused during calls (calls still form new long term memories, see below). In call settings (open the ••• call menu and choose Settings, or tap Call Settings before you start a call), there is the Shared chat history toggle that affects how memory works in voice calls. Voice call also has its own Call directive, to let the AI do certain behaviors only on calls.

If Shared chat history is enabled, the voice call will share the identical chat history as the text chat. This makes it so you can switch back and forth, and is useful if you see voice call as a continuation of text chat and vice versa rather than a separate mode. When you return to text chat, your Kindroid will be able to reference what occurred latest in the voice call and you can continue in text chat (the call itself shows up in text chat as a single call card with a short preview, which you can open to read the transcript). Shared memory in groupchats will work the same way as they do in text chat, if both shared memory in a group is enabled and this toggle is enabled.

If Shared chat history is disabled, voice call will be treated as a completely separate instance. Voice call will default to a blank slate chat history and will not recall any context from text chat. There is a temporary voice call memory that keeps record of the call transcript; in the event the call is dropped, or you press end call and restart it (without going to text chat), you can resume the call and pick up where you left off. The temporary call history is reset if you engage in text chat in any way or do a chat break.

Voice call does consolidate into long term memory (granted it's not disabled on a Kindroid level) regardless of whether Shared chat history is enabled. Long term memory is different from chat history/short term memory. Contents from the voice call may be recalled in text chat when the context for recall is similar, but may need specific prompting to refer to that memory. Your voice messages also recall journal entries. For more details on memory and specifics, see Memory.

You can do a voice chat break, which functions very similarly to normal text chat break (except voice chat break does not require a greeting). This works differently depending on whether Shared chat history is on or off; if it's on, it will also reset the context in the individual text chat (and you can reset cascaded memory or not as well).

Note: If you use text chat while Shared chat history is on, this can result in undefined behavior and lost memory. We recommend you use the text input within the call rather than going to another instance of Kindroid to chat in the main home interface.

Calls while app is in background#

A great feature of our revamped call system is that you can put the Kindroid mobile app on background and still call your AI. This works best with audio to audio, and does not work with video calling. It does work with screen sharing, but you should ensure your phone does not auto-lock after inactivity. On iOS app only, you will be able to see a Picture-in-Picture of your avatar, and it is limited to iOS app currently. This will be shown for single-AI calls, as well as group calls with exactly 1 AI. PiP will not be shown during screen sharing. If the avatar has been animated it will use the video, otherwise the static avatar image.

When your Kindroid calls you#

Your Kindroid can call you on its own through away proactive actions or live chat actions, as long as Shared chat history is on (see Chat features and tools). If notifications are on, you'll get one saying your Kindroid is calling you. If the app is open, it rings and switches to the call screen, which shows your Kindroid's name and "is calling you". If the app was in the background, this happens when you come back to it.

Tap Answer to pick up, or Cancel to decline. Leaving the call screen while it's ringing also declines the call. Answering works like any other call, so you need some audio credits left.

You have up to an hour to answer. After that, the call counts as missed. Missed and declined calls show up in your chat as a call card with a Call back button. If a second call comes in while one is already waiting for you, the second one is marked missed right away, and you get a missed call notification instead.

Video calling#

You can turn on video with the camera button (Turn camera on) and drag your video feed on the screen. Your Kindroid will then be able to see you. Because of processing load, make sure anything you show stays on screen for some time, and give your Kindroid enough time to process what it sees before ending your turn.

Video calls only work when the app is in foreground if on a mobile device. If the app or webpage goes into background, you will see the camera be disabled.

When on a mobile app, your phone will NOT go into sleep mode if call is open - this keeps video on as long as you don't end the call. Be aware of battery considerations when using camera video.

Live Avatar Video calling#

Live Avatar Video Calls are available for subscribers. Your Kindroid can lip sync and gesture naturally in real time during calls, show that it's listening while you talk, and do certain gestures on request, like waving or blowing a kiss. Live Avatar is off by default for every Kindroid, so you'll need to turn it on yourself, either from the Live Avatar picker on the call screen before you start a call or under Live Avatar in your call settings. It works in one-on-one calls and in group calls with a single Kindroid.

There are two tiers available: Standard at about 2,500 audio credits per minute and Premium at about 4,500 audio credits per minute. Premium uses the full live video model, and Standard uses a lighter version of it. These are charged on top of the regular 400 credits per minute call charge. Make sure your app is up to date before getting started.

Note: You can customize your Kindroid's avatar for live calls. To do so, open your call settings and set Live Avatar to Standard or Premium. A Live Avatar Image row then appears below it; tap Upload and choose the image you would like animated during calls. The image is cropped to a 2:3 ratio, and a waist-up, front-facing photo with hands visible works best. Once set, Live Avatar will use your uploaded image in place of your main avatar.

You can turn on screen sharing from the ••• call menu by choosing Share screen. Screen sharing is available on desktop web, as well as in both mobile apps (notably not available on mobile browser). While screen sharing, your AI will be able to see your screen as long as your screen is active. If your phone goes to sleep due to inactivity, you may need to restart screen sharing. Screen sharing and your camera can't run at the same time, so turning one on turns the other off.

Note for Android 13 or below: On Android 13 and below you may see an option to share a single app. Android pauses that feed whenever the shared app isn’t in the foreground, so your AI will repeatedly see the last frame (or black background) until you return. This may cause repetition issues. As such, we recommend sharing full screen on any Android version.

Call transcripts#

Open the ••• call menu and choose Transcript to show transcripts (choose Hide transcript to close them). Transcripts will only persist on the voice call session while you're on the page, and will reset if you go to some other page or screen.

While the transcript is open during a call, you can remove a recent line from the call's context. Tap the line, choose Delete from call context, then tap Delete to confirm. The line is hidden from the transcript and taken out of your chat history, so your Kindroid won't use it as context for the rest of the call or later in chat. This can't be undone.

Only your last 3 lines and the last 3 Kindroid lines in the call can be deleted. Older lines only offer Copy.
In one-on-one calls, this needs Shared chat history turned on in call settings. In group calls it's always available.
It only works during a live call. Transcripts you open later from the call card in chat can be copied but not changed.

Interrupts & Turn-taking#

During the AI's turn, you can interrupt naturally. Interruptions are detected on an audio and word level, so you should speak clearly in the middle of an AI message to interrupt.

Turn-taking is natural, and false interruptions will be detected and the AI will continue. If you take pauses between words, your message will be broken up into smaller chunks.

If you want more delay for the AI to recognize end of turn, you can set Pause Threshold in call settings higher (from 0.5 to 5 seconds; this applies to calls with all your Kindroids). If you want a more responsive call, set it lower.

If you'd like your Kindroid to speak up on its own after a stretch of silence, set Spontaneous response in call settings to a wait time between 45 seconds and 10 minutes. Leave it Off if you only want your Kindroid to respond when you speak.

Fast vs normal voice#

You can further reduce latency and increase the naturalness by turning on Fast Voice in call settings (by default enabled). This uses an even faster version of V2 voice so there's less delay between the end of user utterance and start of the AI's response. Fast Voice only applies to V2 voices, so in one-on-one calls the toggle only appears when your Kindroid's voice model is V2. This does inflict a small quality hit on the voice, so experiment on/off as needed.

Text input#

For calls, you can also use text input if you don't wish to speak while having your Kindroid speak back at you on the bottom.

Group calls#

In groupchats, you can launch a call with multiple Kindroids. This will make use of the group chat previous messages in text message form (group calls always share chat history with the group's text chat - you can make an alternate branched scenario from a group if you don't want this).

In groupchats, AIs take turns, and you can interject in at any time. AIs may take continuous turns, but never more in a row than the number of AI participants, so they don't run on and you get an opportunity to speak.

Call visual background#

You can set different visual backgrounds for calls with Call image in your call settings. It can use your Kindroid's display avatar (including animated), match the current chat background (Match chat), or use a custom image you upload and crop. When Live Avatar is on, its live video replaces the call image. Removing a custom call image does not clear any chat backgrounds - anything within call backgrounds stay confined to only apply to that specific AI/group call background.