n8n-nodes-dualtran

The DualTran node for n8n: translate text inside your workflows with
Google (free, no account) or your own AI model (BYOK, 20+ providers) —
powered by @dualtran/core, the engine extracted from the
DualTran browser extension.

Operations

• Translate Text — translate one text (expressions welcome); output:
  { translation, targetLanguage }.
• Translate Batch — translate a list of texts in one batched request;
  output: { translations: [...], targetLanguage }.

Both support Source Language (auto detects) and Target Language.
The Google engine needs no credentials. The AI (BYOK) engine uses the
DualTran API credential (provider, API key, model, optional base URL) —
your key, sent only to your provider.

Install

Self-hosted n8n

Settings → Community nodes → Install → n8n-nodes-dualtran
(or npm install n8n-nodes-dualtran into ~/.n8n/nodes on your instance).

Development

node scripts/sync-core.mjs   # stages dualtran-core/ (CJS + ESM core builds)
npm install
npm test                     # vitest: translate logic + static contract + real core integration
npm run build                # n8n-node build → dist/
npm run lint                 # n8n-node lint
npm run verify               # test + build + lint

Node reference

On failure the node honours Continue On Fail (emits { error } and keeps
the workflow running) or throws a node error with the item index.

License

MIT — the bundled @dualtran/core portion is MPL-2.0.