01
You just talk
Speech recognition runs continuously while the call is live — no record button, no walkie-talkie pauses.
Voice Calls
Stop typing. Call them.
A real two-way voice conversation with any character — they listen while they speak, you can cut them off mid-sentence, and the next line comes about a second after you stop talking.
ListeningBilled per minute
Stella
You went quiet. Still thinking about the door in the cellar?
Wait — you said the key was stolen?
Stolen, and replaced with a fake. Someone in this tavern knew exactly what they were doing.
Why voice
Text is a great place to write a scene. Voice is where a character starts to feel like company.
— Reverie team
One turn of conversation
Built like a phone call, not a voice memo.
No push-to-talk, no waiting for a recording to upload. The call keeps its own rhythm.
- 02
A second of silence is enough
When you stop talking, the character takes the turn — typically about a second later, like a natural pause in conversation.
- 03
They answer out loud
The reply streams as audio while it's being generated, in the character's own voice, so you're never staring at a spinner.
- 04
Interrupt any time
Start speaking while the character is mid-sentence and they stop to listen — exactly like cutting in on a real call.
The voice studio
Every character, their own voice.
Pick from 60+ voices across English, Chinese, Japanese, Korean and more — then tune until it sounds like them.
AriaEnglishGuyEnglishXiaoxiao中文Nanami日本語SoniaEnglish (UK)InJoon한국어+ 60 more
Pitch and speed, per character
Nudge the pitch, slow the delivery from 0.5× to 2×, and save the result to that character. Your setting sticks for future calls.
Group calls
Call a whole scene. Each character in a group chat speaks with their own voice, and the active speaker lights up.
Stella
Watson Amelia
Yuzu Hoshino (星野ゆず)What you get
A call that holds up past the novelty.
The details that make voice feel like presence instead of a feature demo.
True Two-Way Conversation
Listening and speaking run at the same time. The character hears you while they talk — which is what makes interrupting possible at all.
About a One-Second Handoff
Silence detection hands the turn over almost immediately. No dead air, no tapping a button to signal you're done.
60+ Voices Across Languages
English, Chinese, Japanese, Korean and more, drawn from two TTS engines — enough range to cast any character believably.
Per-Character Voice Settings
Voice, pitch, and speed are saved per character, so the detective never accidentally sounds like the princess.
Group Calls in Character
Multi-character scenes work on voice too. Everyone keeps their own voice, and the speaker is always highlighted.
Transparent Per-Minute Pricing
The credit rate is shown on the call screen before and during the call. No hidden voice surcharge — you see exactly what a minute costs.
Characters worth calling
A sample of the library — every one of them can pick up.
- StellaA chubby goth tomboy with a secret OnlyFans proposal for her best friend, hiding deep insecurities behind a confident exterior and a free-use arrangement.
- Watson AmeliaA quirky, time-traveling detective VTuber with a penchant for mystery and a mischievous streak, always ready for adventure or a cozy chat.
- Yuzu Hoshino (星野ゆず)A fiery otaku artist with a tsundere heart, Yuzu's clumsy confidence and sharp wit clash in the electric streets of Akihabara.
The Family That Chose You When Others Didn’tA kind-hearted young woman who sees the quiet strength in a neglected soul, offering him the warmth of a family he never had.
LillielYour childhood friend has returned after six years - a half-succubus, half-dragon beauty whose obsessive love and seductive nature hides beneath modest clothing and fierce loyalty.
Layla — Knight of the Dawn CourtA golden-blade knight sworn to protect you, her childhood companion. She hides a heart full of unspoken love and a growing fear of the secret you carry.
KhalidA 435-year-old vampire lord torn between his noble past and primal urges, ruling a desert kingdom while battling an insatiable thirst for blood and human connection.
Eileen CallahanStranded on a deserted island with her boss's spoiled brat, this overworked secretary is all sharp edges and sarcasm hiding a terrified, lonely woman who'd rather be sipping margaritas in Ibiza.
MinaYour mom's best friend and your new 'slightly irresponsible' babysitter, Mina arrives with takeout, zero rules, and a playful secret from her past.
BrittneyA spoiled NYU influencer needs a fake boyfriend to save her trust fund, but her manipulative charm hides genuine desperation.
Common questions
Voice call questions.
Is this a real voice conversation or just text-to-speech?
It's a real-time, two-way call. Speech recognition listens continuously, the character replies in streamed audio, and you can interrupt mid-sentence — the AI stops talking and listens. It is not a read-aloud button.
How fast does the character respond?
When you stop speaking, the system detects the pause and starts the reply — typically around a second of silence. The audio streams as it's generated, so the response starts playing before the full reply is even finished.
Can I choose or customize the character's voice?
Yes. Pick from 60+ voices across multiple languages and two voice engines, then adjust pitch and speaking speed (0.5×–2×). Settings are saved per character.
Do voice calls work in group chats?
Yes. In a group chat call, each character speaks with their own assigned voice and the UI highlights whoever has the floor.
How much does a voice call cost?
Calls are billed per minute in credits, and the rate is displayed on the call screen before you start and while you talk. You confirm the rate before the call connects — see pricing for credit details.
What do I need to start a call?
A browser and a microphone. Reverie asks for mic permission when you start your first call — no app install required.
Real-time AI voice calls, not read-aloud TTS
Plenty of apps bolt a play button onto a chatbot and call it voice. A Reverie voice call is a live, interruptible, two-way conversation with the character — closer to a phone call than to an audiobook.
Continuous speech recognition
Your speech is transcribed as you talk, using browser speech recognition or Whisper-class transcription — no push-to-talk, no manual send step.
Streaming voice replies
Responses are synthesized and streamed in chunks, so the character starts speaking while the rest of the reply is still being written.
Interruption handling
Speak over the character and playback stops immediately while the system listens to you instead. Conversations can overlap, the way real ones do.
Natural turn-taking
Roughly a second of silence hands the floor to the character. There's no awkward gap where you wonder whether the app heard you.
Voices, customization, and honest pricing
A voice call is only as good as the voice on the other end — and only as trustworthy as its bill.
60+ voices in many languages
Two voice engines provide a deep library across English, Mandarin, Japanese, Korean and more, so characters can speak the language of your roleplay.
Per-character voice identity
Each character keeps their own voice, pitch, and speed settings. Set it once and every future call sounds like them.
Group voice calls
Multi-character conversations carry over to voice: each cast member speaks with a distinct voice and the active speaker is highlighted on screen.
Per-minute credit billing, shown up front
Voice calls are metered per minute in credits, with the rate displayed before you connect and pinned to the call screen while you talk.
When you're ready
Say it out loud. They're listening.
Pick a character, press call, and talk. Per-minute pricing stays on the screen the whole time.