Live Translate
Company-governed translation for frontline conversations — runs through your own provider, inside your tenant, nothing stored.
MangoApps
Overview
Live Translate is company-governed translation for the frontline — the interpreter your compliance team can actually approve. Where consumer translate apps can't be used with sensitive workplace information (patient data, customer PII, incident details, HR conversations), Live Translate runs through your organization's OWN translation provider, keeps every conversation ephemeral (nothing is stored), and stays inside your tenant boundary — so you can sanction one tool instead of prohibiting the rest. The interpreter itself is turn-based and speech-to-speech: two people share one phone (or pair two phones with a short session code), each holds a button to talk and hears the other spoken back in their own language, across 15 languages. Built for the frontline moment a manager and an associate clearing a language barrier on the floor. Continuous, always-on conversation mode is a later phase; today it is push-to-talk, turn-based.
Highlights
Capabilities
Company-governed & private
-
Runs through your organization's own translation provider (bring-your-own AWS Translate or DeepL)
-
Managed AWS Translate default when no provider is configured
-
Falls back to the platform LLM so it works with zero setup
-
Ephemeral sessions — no turn or transcript is stored
-
Names the active provider in-app so users see who is translating
Speak & hear (turn-based interpreter)
-
Push-to-talk, turn-based speech-to-speech interpretation
-
Spoken playback in the listener's language (not just text)
-
On-screen transcript of the exchange (source + translation)
-
Automatic speaker-language detection ("Detect")
One device or two
-
Single-device mode (two people share one phone)
-
Paired two-device mode over a short session code
-
Host admits the joiner — only the pair can inject turns into a session
-
Remembers each side's language across visits
Company glossary
-
Company terminology enforced provider-independently (protect → translate → restore)
-
Term mappings — a source term always renders as your approved target
-
Do-not-translate terms — brands, SKUs, and codes pass through untouched
-
Case-sensitive term matching option
-
Glossary managed by admins at /admin/translation
Safeguards & metering
-
Per-user hourly rate limits on turns and session creation
-
App enablement plus per-user visibility gating
-
Every turn's AI usage logged for cost tracking
Limits & Specs
-
Languages: 15, plus automatic Detect of the speaker's language
-
Turns per user, per hour: 200
-
Paired sessions per hour: 60
-
Max recording per turn: 15 MB (short push-to-talk turns)
-
Translation engines: AWS Translate, DeepL, or the platform LLM
-
Speech in / out: OpenAI Whisper (transcribe) / OpenAI TTS (speak)
-
Pricing: Pay-as-you-go — no license; Whisper, translation, and TTS meter through your AI/Voice credit pool
Use cases
Resources
FAQ
No. Live Translate sessions are ephemeral — turns are transcribed, translated, and spoken back in real time, and nothing is persisted.
It uses your configured translation provider — a dedicated machine-translation engine such as AWS Translate or DeepL when set, otherwise the platform LLM — so it follows the same company-governed provider you configure for the rest of the product.
It is turn-based: each speaker holds to talk, and the other hears the translation spoken back. Always-on, full-duplex call translation is a later phase.
Pay-as-you-go. There is no license to buy — every tenant can turn it on, and the Whisper, machine-translation, and text-to-speech usage each turn consumes is metered through your existing AI/Voice credit pool.
Yes. Your company glossary — both term mappings and do-not-translate rules — is applied on every turn, provider-independently, and is managed by admins at /admin/translation.
Fifteen languages out of the box — English, Spanish, French, German, Portuguese, Italian, Chinese, Japanese, Korean, Arabic, Hindi, Russian, Vietnamese, Tagalog, and Polish — plus a "Detect language" option that lets the app recognize the speaker's language automatically so a source language doesn't have to be picked ahead of time.
No. If your organization sets up its own provider (AWS Translate or DeepL), Live Translate runs through it; if none is configured, it uses a managed AWS Translate default and ultimately falls back to the platform LLM, so it works with zero setup. Speech-in (Whisper) and speech-out (text-to-speech) run on the platform's OpenAI connection, so those must be available for a turn to run.
Yes. Beyond single-device mode (two people sharing one phone), one person can create a paired session and share a short code; the other joins from their own phone and hears each turn spoken in their own language. The host admits the joiner, and only that pair can inject turns — a third person who happens to have the code cannot join or add audio to the conversation.
No. Live Translate is a spoken interpreter — you hold a button to talk and the other person hears the translation played back. There is no type-to-translate text box; it is speech-in, speech-out only.
They are separate apps for different needs. Live Assist is real-time "see what I see" video help — a remote expert joining a live video/screen-share session launched from a work object. Live Translate is a spoken language interpreter for clearing a language barrier in a face-to-face or two-phone conversation. Use Live Assist when someone needs to show a problem on camera; use Live Translate when two people need to understand each other across languages.
