Live · paid
Live translated calls
Call across languages and each sentence is transcribed, translated, and re-spoken in your cloned voice in real time. WebRTC carries your raw voice in parallel, so you always hear something.
Products
One inbox, every language, your voice.
Call across languages. Send voice messages in your cloned voice. Text, dub video, and share media in a single thread. Translation runs automatically across every channel — no toggles, no copy-paste, no mode switching.
Early access
Interpreter mode
One app on the table translates a live back-and-forth conversation between two languages — auto-detecting who is speaking, in your cloned voice. In early access.
Free
Voice messages
Tap, talk, send. The recipient hears it in your cloned voice in their language — with the same emotion you put into the recording. Free.
Free
Texts
Type in your language. They read in theirs — or either side can play the text aloud in the voice tone you chose when you sent it. Replies are translated back the same way. Free.
Free
Video translation & dubs
Re-voice a video into another language in your own voice. Free — no minute metering.
Free
Photos & media
Share photos and videos in the same WhatsApp / MMS-style thread as your calls and texts. Free.
One voice engine
One engine, tuned for a single job: sounding like you.
We run a single high-quality voice-cloning engine across every channel — no confusing tiers to pick. It clones your timbre from a short recording and re-speaks translated text in your own voice.
⟁
Five emotion baselines
Record neutral, excited, angry, sad, and whisper once. The right tone rides along automatically on calls and voice messages.
⟁
Custom tones
Add your own named tones on top of the five baselines and pick one at send time.
⟁
Emotion-aware on live calls
On live calls and voice messages, the emotion in your real delivery carries through to the translation — not a text-to-speech robot.
The pipeline
How a sentence becomes a translated sentence — in your voice.
- 1
On-device speech recognition
On live calls, your speech is recognized right on your phone in real time — nothing waits on a round-trip to the server. (Voice messages and interpreter mode transcribe on our servers.)
- 2
Translation
A fast translation layer converts each sentence into the target language, backed by an open-source engine as a fallback so it keeps working across every language we support. It uses your recent conversation for context to disambiguate.
- 3
Voice-cloned synthesis
The translated message lands in your cloned voice on the other side. For live calls and voice messages, the emotion in your real-time speech carries through automatically. For texts, you pick one of your recorded tones at send time — and either side can play the text aloud. Either way, the other person hears you.
- 4
Delivery on every channel
Live calls ride a parallel WebRTC audio plane so you always hear something. Voice messages, texts, and media land in the same translated thread.
Why live translation is the only thing you pay for
Almost everything in TranslationTone is free. A live translated call needs dedicated GPU compute running in real time for your whole conversation — we spin one up for you, usually within about 30 seconds. That real-time compute is the one thing minutes pay for.
On the roadmap
The same words, the right register — coming next.
We're training audience-specific translation models so you'll be able to pick a register before your call or thread. Today's translations use a general-purpose model; the feedback loop — the “fix this translation” button on every call and message — trains the audiences below directly.
General
Everyday calls — neutral register, broad vocabulary.
Family
Warmer phrasing tuned for grandparents, kids, partners.
Business
Formal tone, careful with names and titles.
Tech
Preserves jargon, code names, version numbers.
Legal
Conservative phrasing for stakes-y conversations.
Medical
Patient-clinician language with precise terminology.