Watch the walkthrough
An illustrated walkthrough using example instructions. The video is in English; use the subtitle menu for another language. Translate must be included in your current plan. The assistant editor keeps every engine mode visible; a locked mode opens its description and a link to the Plan page. The same workspace plan rule applies when rooms are created through the API or MCP.Start on iOS or Android
- Open the Translate tab. Choose a saved assistant on the first screen, or tap Get started or Create a Translate assistant to make a new one.
- Choose each person’s spoken language. Pick the voice that represents each person in the other person’s language. Tap Open translation room. The app names a new assistant after the selected languages, such as German ↔ English.
- Under Participation, tap a person to choose how they join. Use App audio to join on your device and Share invitation to invite your guest in their browser. Choose By phone to call a person when you start.
Prepare a conversation
- On the dashboard, select AI Translate next to New Assistant. You can also find AI Translate after the role cards in the assistant wizard.
- Choose the two spoken languages under I speak and My guest speaks. AI Translate picks compatible voices from the library.
- Select Open translation room. The workspace saves the language pair for next time.
- Choose how each person joins, invite your conversation partner, and select Start conversation.
Choose voices
The voice selected for a speaker represents that speaker in the other person’s language. If Tobias is Speaker 1, Aleksandra hears the Speaker 1 voice speaking Polish. Tobias hears the Speaker 2 voice speaking German. Use an available library voice or an authorized workspace voice clone. The picker shows voices compatible with the listener’s language. Some library voices are not offered for Translate. List the voices you can save withGET /api/v1/voices?translation=true, the MCP tool get_voices with translation set to true, famulor list-voices --translation, or client.voices.list({ translation: true }). Saving any other voice is rejected. A private workspace voice can speak to a guest without giving that guest access to the voice library or the clone itself.
Web and phone participation
Call requires a connected outgoing number. If none is available, call controls remain disabled. Dial in uses the incoming connection independently and does not require an outgoing number. Choose the country beside each destination number; the field includes its international dialing code. The guest can use Web or Call with any of Speaker 1’s three options.
For dial-in, the assigned number is shown while you prepare the conversation. The six-digit code appears after you start the room and remains visible beside the number. Code entry has a 30-second window, including the spoken prompts, with at most three incorrect attempts. Entering the correct code before the room starts does not use an attempt; the call explains that the host must start the room first.
Each speaker uses one audio connection. When a person participates by phone, their browser becomes a transcript observer with its microphone and sound off. Leaving browser audio does not hang up a phone connection. The host can end the whole conversation with End conversation. Before the conversation starts, Close room closes the room and its invitation. Both ask for confirmation first.
Use headphones for browser calls. If the browser blocks playback, select Enable translated audio. If microphone permission is denied, allow it in the browser’s site settings and try joining again.