PTranslator

Features

Offline voice translation written in Go: speak in any language, hear it in another.

A whole interpreter on your computer

Four steps in one pipeline — and nothing to sign up for.

Models are downloaded once and verified; after that it works without a network. Nothing you say is uploaded.

Speak in any supported language; PTranslator detects it for each sentence, so a conversation can switch languages.

Any pair of Vietnamese, Japanese, Korean, French and Chinese goes through English, using Mozilla's open Firefox Translations models.

A natural synthetic voice in the target language, with ten voices and adjustable speed.

Missing models are fetched with their size and licence shown first, resumable, checked by checksum, and kept under a memory limit.

Every sentence reports the time of each stage, and the project documents its known limits and test results openly.

Five stages run in parallel, so the next sentence can already be heard while this one is spoken.

1
Listen
The microphone is watched by a voice-activity detector that cuts the audio into sentences.
2
Recognise
Whisper turns speech into text and detects the language.
3
Translate
The sentence is translated, through English when neither side is English.
4
Speak
A synthetic voice reads the translation in the target language.
5
Show
The original, the translation and the time of each stage are printed.

Tell us the languages and the situations you need it for.