Gladia · Agentic Access

Gladia Agentic Access

x-agentic-access generated

Gladia exposes 21 API operations that an AI agent could call, of which 10 are state-changing ‘acting’ operations. This is a recommended x-agentic-access execution contract — the scope, audience, consequence tier, short-lived token constraints, and escalation each action should carry before it is handed to an autonomous agent.

By consequence: 11 read and 10 safety-critical.

10 operations are classed safety-critical and should require human-in-the-loop approval at runtime.

Contracts are classified heuristically from the provider’s OpenAPI and refresh on every APIs.io network build; audience is bound per deployment. The model follows Curity’s Access Intelligence (apidays Munich 2026). Browse every provider’s agent contracts at agentic-access.apis.io.

Speech-to-TextTranscriptionAudio IntelligenceReal-TimeSpeaker DiarizationTranslationWebSocketREST
Operations: 21 Acting: 10 Human-in-the-loop: 10 Method: generated

By consequence

read 11 safety-critical 10

Highest-consequence actions

The physical and safety-critical operations an agent could invoke — the ones that most warrant scoped tokens, tight TTLs, and escalation. Full per-operation contracts are in the source below.

MethodPathConsequenceHuman-in-loop
POST /audio/text/audio-transcription safety-critical required
POST /v2/live safety-critical required
DELETE /v2/live/{id} safety-critical required
PATCH /v2/live/{id} safety-critical required
POST /v2/pre-recorded safety-critical required
DELETE /v2/pre-recorded/{id} safety-critical required
POST /v2/transcription safety-critical required
DELETE /v2/transcription/{id} safety-critical required
POST /v2/upload safety-critical required
POST /video/text/video-transcription safety-critical required

Source

Agentic Access

Raw ↑ 
generated: '2026-07-15'
method: generated
source: openapi/gladia-control-api-openapi.yml
description: Recommended x-agentic-access execution contracts, classified heuristically from
  the OpenAPI. A governance starting point for exposing this API to AI agents — review and bind
  audience per deployment. See research/curity/agentic-governance/.
summary:
  operations: 21
  by_action_class:
    acting: 10
    connected: 11
  by_consequence:
    safety-critical: 10
    read: 11
  human_in_the_loop_required: 10
operations:
- path: /v2/upload
  method: post
  operationId: FileController_upload_v2
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /v2/pre-recorded
  method: post
  operationId: PreRecordedController_initPreRecordedJob_v2
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /v2/pre-recorded
  method: get
  operationId: PreRecordedController_getPreRecordedJobs_v2
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/pre-recorded/{id}
  method: get
  operationId: PreRecordedController_getPreRecordedJob_v2
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/pre-recorded/{id}
  method: delete
  operationId: PreRecordedController_deletePreRecordedJob_v2
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /v2/pre-recorded/{id}/file
  method: get
  operationId: PreRecordedController_getAudio_v2
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/transcription
  method: post
  operationId: TranscriptionController_initPreRecordedJob_v2
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /v2/transcription
  method: get
  operationId: TranscriptionController_list_v2
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/transcription/{id}
  method: get
  operationId: TranscriptionController_getTranscript_v2
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/transcription/{id}
  method: delete
  operationId: TranscriptionController_deleteTranscript_v2
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /v2/transcription/{id}/file
  method: get
  operationId: TranscriptionController_getAudio_v2
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /audio/text/audio-transcription
  method: post
  operationId: AudioToTextController_audioTranscription
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /video/text/video-transcription
  method: post
  operationId: VideoToTextController_videoTranscription
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /v1/history
  method: get
  operationId: HistoryController_getList_v1
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/live
  method: post
  operationId: StreamingController_initStreamingSession_v2
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /v2/live
  method: get
  operationId: StreamingController_getStreamingJobs_v2
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/live/{id}
  method: get
  operationId: StreamingController_getStreamingJob_v2
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/live/{id}
  method: delete
  operationId: StreamingController_deleteStreamingJob_v2
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /v2/live/{id}
  method: patch
  operationId: StreamingController_patchRequestParams_v2
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /v2/live/{id}/file
  method: get
  operationId: StreamingController_getAudio_v2
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v1/models
  method: get
  operationId: ModelsController_list_v1
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none