Private English speech-to-text for AI assistants. Transcribe a public HTTPS audio link, a one-time file upload, or an inline clip, with optional word timestamps and speaker labels. Audio is processed in memory on our own hardware in North Carolina, then erased, without training on recordings. Requires a Loquela Remote account and subscription or prepaid minutes. Beta service for US customers; English audio only. Docs: https://docs.getloquela.com/remote/mcp
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 5 tools
Each tool has a clearly distinct role: get_usage is separate, create_upload_link creates a link, and the three transcribe_* tools differ by input source (inline base64, upload link, public URL). The descriptions explicitly cross-reference each other, so an agent can reliably select the right transcription path.
All tool names use snake_case and follow a predictable verb_noun pattern (create_upload_link, get_usage, transcribe_audio, transcribe_upload, transcribe_url). The transcribe_* family is especially consistent, with suffixes that clearly indicate the input modality.
Five tools are well-scoped for a focused audio transcription service. Each tool earns its place: one usage tool, one upload-link tool, and three transcription variants for different input sources.
The surface covers the main transcription workflows (inline audio, local file upload, public URL) plus account usage, with no obvious dead ends. Minor gaps exist around transcript history/retrieval or upload cancellation, but agents can accomplish the core task.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
transcribe_audio1 field changedInput schema / properties / written_numbersAdded value: +{
+ "default": null,
+ "description": "Write spoken numbers as digits (\"8.3%\", \"$2.5 billion\", \"2021\"). Leave out for the default (digits); false keeps the model's own wording, which often spells numbers out.",
+ "type": [
+ "boolean",
+ "null"
+ ]
+}transcribe_upload1 field changedInput schema / properties / written_numbersAdded value: +{
+ "default": null,
+ "description": "Write spoken numbers as digits (\"8.3%\", \"$2.5 billion\", \"2021\"). Leave out for the default (digits); false keeps the model's own wording, which often spells numbers out.",
+ "type": [
+ "boolean",
+ "null"
+ ]
+}transcribe_url1 field changedInput schema / properties / written_numbersAdded value: +{
+ "default": null,
+ "description": "Write spoken numbers as digits (\"8.3%\", \"$2.5 billion\", \"2021\"). Leave out for the default (digits); false keeps the model's own wording, which often spells numbers out.",
+ "type": [
+ "boolean",
+ "null"
+ ]
+}create_upload_linkget_usagetranscribe_audiotranscribe_uploadtranscribe_url
Add one secure layer between your agents and this server.