Gladia
Transcribe pre-recorded audio and video with Gladia: submit a job, poll its result, list and delete jobs, and register a remote file.
About
Gladia ships in the w6w first-party pack. It declares 6 actions, 3 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.gladia- Version
- 0.1.0
- Author
- w6w
- Licence
- MIT
- Categories
- AI & Machine Learning · Video & Streaming
Overview
Gladia is a speech-to-text API for audio and video. This app starts pre-recorded transcription jobs from an audio URL (with language selection, speaker diarization, subtitles, translation, summarization, sentences, named entities, sentiment, custom vocabulary and spelling, PII redaction and a completion callback), reads a job’s status and result, lists and deletes jobs, registers a remote file with Gladia, and lists the available models. Live (WebSocket) streaming is not covered.
Build with Gladia
Three routes to the same 6 actions. The Workflow tab is generated from Gladia's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
Upload Audio URL
audio-upload-url Have Gladia fetch a remote audio or video file and return a Gladia-hosted audio_url with its detected duration, size and channel count.
Delete Transcription
transcription-delete Delete a pre-recorded job and all its data (audio file and transcript).
Get Transcription
transcription-get Get a pre-recorded job's status and, once status is "done", its result.
List Transcriptions
transcription-list List pre-recorded jobs, optionally filtered by status and date.
Start Transcription
transcription-start Start an asynchronous pre-recorded transcription job from an audio or video URL. Returns the job id; fetch the result with Get Transcription.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Gladia's real ids.
{
"manifestVersion": "2",
"name": "gladia-example",
"steps": [
{
"id": "audio-upload-url",
"uses": {
"app": "io.w6w.gladia",
"action": "audio-upload-url",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"audioUrl": "<audioUrl>"
}
}
]
}Here are some of the things you can do
-
Upload Audio URL
performaudio-upload-url -
List Models
readmodel-list -
Get Transcription
readtranscription-get -
List Transcriptions
searchtranscription-list -
Start Transcription
performtranscription-start
+1 more action available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Gladia, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Gladia. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "audio-upload-url",
payload: {
audioUrl: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action audio-upload-url --payload '{"audioUrl":"<value>"}'Give an AI agent Gladia — without giving it Gladia's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.gladia#audio-upload-url",
"input": {
"audioUrl": "<audioUrl>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Gladia connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
A tool surface scoped to the caller
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
A durable workflow in one call
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Health-aware discovery
Gladia's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Gladia itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
Gladia declares its own checks, so its health is a property of the app rather than something the host guesses at.
Gladia platform status
status.gladia.io (Statuspage-compatible). The `API` and `Pre-Recorded v2` components decide; Real-Time, Website, Playground and Add-ons are detail capped at degraded.
API reachability
Unauthenticated GET of api.gladia.io/v2/pre-recorded. The documented 401 error envelope is the healthy answer; credential validity is the `auth:api-key` check's job.