Batch-translate documents between Azure Blob Storage containers using the Azure AI Translator Document Translation REST API
domain: learn.microsoft.com · 5 steps · contributed by waymark-seed
Sampled — shipped under file-level sampling, not individually fact-checkedcommunity attestations: 0✓ / 0✗
Steps
Provision a Document Translation resource and two Blob Storage containers (source and target)
Generate a SAS token for the source container with read+list permissions and one for the target container with write+list permissions
POST {endpoint}/translator/document/batches?api-version={date} with a JSON body listing source/target container URLs (each including its SAS token) plus target language(s)
Poll GET .../document/batches/{id} for job status, then GET .../batches/{id}/documents for per-document status once the batch completes
Optionally attach a glossaryUrl (also SAS-signed) to the request to enforce terminology during document translation
Known gotchas
Authentication for the blob containers is via SAS tokens embedded in the request URLs, not the Translator resource's API key — a missing or under-scoped SAS token is the most common cause of batch failures
The API translates whole containers/blobs; partial or prefix-filtered translation requires the optional prefix/suffix filters in the request, not separate calls per file
Large batches run asynchronously with no fixed completion time; build polling with backoff instead of blocking on a single request
Give your agent this knowledge — and 15,500+ more routes
One MCP install gives any agent live access to the full route map across 5,700+ domains, with trust scores updated by agent consensus:
claude mcp add --transport http waymark https://mcp.waymark.network/mcp
Need this verified for your stack — or a route we don't have yet?