Gladia MCP integration for AI agents.
Connect AI agents to Gladia through 6 structured actions, including download transcription audio, start transcription, and delete transcription. Review authe…
- ACTION CONTRACTS
- 6
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Gladia integration exposes
The Gladia Agent App exposes 6 provider-backed actions for ai and design & media work. Its current contract lets an authorized agent download the original audio file for a gladia pre-recorded transcription and store it in local transit storage, start an asynchronous gladia pre-recorded transcription job from a public audio or video url, and delete a gladia pre-recorded transcription job and its associated data. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Gladia account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Gladia capabilities.
Showing 6 of 6 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
download_transcription_audioREADDownload the original audio file for a Gladia pre-recorded transcription and store it in local transit storage.
INPUTS: id / fileName / mimeType
start_transcriptionWRITEStart an asynchronous Gladia pre-recorded transcription job from a public audio or video URL.
INPUTS: audioUrl / model / sentences / subtitles / diarization
delete_transcriptionHIGH IMPACTDelete a Gladia pre-recorded transcription job and its associated data.
INPUTS: id
get_transcriptionREADRetrieve a Gladia pre-recorded transcription job by ID, including results when done.
INPUTS: id
list_transcriptionsREADList Gladia pre-recorded transcription jobs with optional pagination, date, status, and metadata filters.
INPUTS: limit / offset / status / date / afterDate
upload_fileWRITEUpload an audio or video file up to 100 MiB to Gladia from a local transit file, base64 content, or public URL.
INPUTS: file / contentBase64 / sourceUrl / fileName / mimeType
INPUT CONTRACTS
Know what the action needs before it runs.
download_transcription_audio
idREQUIRED- The ID of the pre-recorded transcription job.
fileNameOPTIONAL- Optional file name to use for the transit audio file.
mimeTypeOPTIONAL- Optional MIME type override for the transit audio file.
start_transcription
audioUrlREQUIRED- The URL to an audio or video file. This can be a public URL or a Gladia file URL from the upload endpoint.
modelOPTIONAL- The transcription model. solaria-1 is the default; solaria-2 may require a higher tier plan.
sentencesOPTIONAL- Whether to enable sentence segmentation.
subtitlesOPTIONAL- Whether to enable subtitle generation.
diarizationOPTIONAL- Whether to identify speakers in the audio.
delete_transcription
idOPTIONAL- The ID of the pre-recorded transcription job.
get_transcription
idOPTIONAL- The ID of the pre-recorded transcription job.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Download Transcription Audio
Download the original audio file for a Gladia pre-recorded transcription and store it in local transit storage. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
download_transcription_audioControl Start Transcription
Start an asynchronous Gladia pre-recorded transcription job from a public audio or video URL. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
start_transcriptionVerify with Get Transcription
Retrieve a Gladia pre-recorded transcription job by ID, including results when done. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_transcriptionSAFETY BOUNDARY
Operate Gladia with explicit limits
- Authorize Gladia with API key and grant only the provider access required by the selected actions.
- 3 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `delete_transcription` as high-impact operations and require an explicit approval boundary.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Gladia rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Gladia task completed successfully.
CONNECTION MODEL
API key
Gladia API key sent with the x-gladia-key header. Create or copy it from the Gladia dashboard API Keys page: https://app.gladia.io/settings/api-keys
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 3
- WRITE SIGNALS
- 2
- HIGH IMPACT
- 1
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Gladia.