Cekura

Cekura Test Framework API

The test_framework API from Cekura — 128 operation(s) for test_framework.

GitHub OpenAPI

Operations 143

GET /test_framework/billing/info/ Get billing information #
GET /test_framework/billing/payment-history/ Get payment history #
GET /test_framework/billing/unit-usage-report/ Get monthly usage and credits per billable unit #
PATCH /test_framework/metric-reviews/{id}/ Update a metric review #
POST /test_framework/metric-reviews/process_feedbacks/ Improve a metric from feedback #
POST /test_framework/metric-reviews/process_feedbacks_answer/ Metric reviews process feedbacks answer #
GET /test_framework/metric-reviews/process_feedbacks_progress/ Get metric improvement progress #
POST /test_framework/test-sets/create_from_call_log/ Create a test set from a production call log #
POST /test_framework/test-sets/create_from_run/ Create a test set from a previous test run #
GET /test_framework/v1/critical-metric-scenarios/ List critical metric scenarios #
PATCH /test_framework/v1/critical-metric-scenarios/{id}/ Update a critical metric scenario #
PATCH /test_framework/v1/metrics-external/reorder/ Reorder project metrics #
DELETE /test_framework/v1/metrics/{id}/ Delete a metric #
POST /test_framework/v1/metrics/{id}/run_reviews/ Metrics run reviews create 2 #
POST /test_framework/v1/metrics/bulk_create/ Create multiple metrics in a single request #
POST /test_framework/v1/metrics/generate_clean_description/ Metrics generate clean description create 2 #
POST /test_framework/v1/metrics/generate_clean_description_bg/ Start async clean description generation #
GET /test_framework/v1/metrics/generate_clean_description_progress/ Poll async clean description generation #
POST /test_framework/v1/metrics/generate_evaluation_trigger/ Metrics generate evaluation trigger create 2 #
POST /test_framework/v1/metrics/generate_metrics/ Metrics generate 2 #
GET /test_framework/v1/metrics/generate_metrics_progress/ Metrics generate metrics progress retrieve 2 #
POST /test_framework/v1/metrics/preview/ Metrics preview create 2 #
GET /test_framework/v1/metrics/preview-progress/ Metrics preview progress 2 #
PATCH /test_framework/v1/metrics/reorder/ Reorder project metrics #
GET /test_framework/v1/metrics/run_reviews_progress/ Metrics run reviews progress 2 #
POST /test_framework/v1/metrics/simplify_prompt/ Metrics simplify prompt create 2 #
GET /test_framework/v1/metrics/simplify_prompt_progress/ Metrics simplify prompt progress retrieve 2 #
GET /test_framework/v1/personalities/ List personalities #
POST /test_framework/v1/personalities/ Create a personality #
POST /test_framework/v1/personalities-external/clone_voice/ Personalities external clone voice create #
GET /test_framework/v1/personalities/{id}/ Retrieve a personality #
PATCH /test_framework/v1/personalities/{id}/ Update a personality #
DELETE /test_framework/v1/personalities/{id}/ Delete a personality #
POST /test_framework/v1/personalities/{id}/fork/ Fork a personality into a project #
GET /test_framework/v1/personalities/cartesia_voices/ List Cartesia voices #
POST /test_framework/v1/personalities/clone_voice/ Personalities clone voice create #
GET /test_framework/v1/personalities/elevenlabs_voices/ List ElevenLabs voices #
GET /test_framework/v1/phone-numbers/inbound/ List inbound phone numbers #
GET /test_framework/v1/predefined-metrics/ List predefined metrics #
POST /test_framework/v1/predefined-metrics/copy/ Attach predefined metrics to a project #
POST /test_framework/v1/results/{id}/evaluate_metrics/ Results evaluate metrics create 2 #
POST /test_framework/v1/results/{id}/rerun/ Re-run the scenarios from a completed test result #
GET /test_framework/v1/runs/{id}/logs/ Retrieve execution logs for a simulation run #
GET /test_framework/v1/runs/{id}/trace/ Get a run's trace #
POST /test_framework/v1/scenario-improvement-sessions/ Create a scenario improvement session #
GET /test_framework/v1/scenario-improvement-sessions/{id}/ Get a scenario improvement session #
PATCH /test_framework/v1/scenario-improvement-sessions/{id}/ Update a scenario improvement session #
GET /test_framework/v1/scenarios/ List evaluators #
PUT /test_framework/v1/scenarios-external/{id}/condition-audio/{audio_id}/ Replace an audio clip's recording #
PATCH /test_framework/v1/scenarios-external/{id}/condition-audio/{audio_id}/ Correct an audio clip's transcript and word timings #
GET /test_framework/v1/scenarios/{id}/ Retrieve an evaluator #
DELETE /test_framework/v1/scenarios/{id}/ Delete an evaluator #
PUT /test_framework/v1/scenarios/{id}/condition-audio/{audio_id}/ Replace an audio clip's recording #
PATCH /test_framework/v1/scenarios/{id}/condition-audio/{audio_id}/ Correct an audio clip's transcript and word timings #
POST /test_framework/v1/scenarios/create-from-transcript-bg/ Scenarios create from transcript bg 2 #
GET /test_framework/v1/scenarios/create-from-transcript-progress/ Scenarios create from transcript progress 2 #
POST /test_framework/v1/scenarios/create_folder/ Create a folder #
POST /test_framework/v1/scenarios/delete_folder/ Scenarios folder delete 2 #
GET /test_framework/v1/scenarios/folders/ Scenarios folders list 2 #
POST /test_framework/v1/scenarios/generate-bg/ Scenarios generate bg 2 #
POST /test_framework/v1/scenarios/generate-instructions/ Scenarios generate instructions create 2 #
GET /test_framework/v1/scenarios/generate-progress/ Scenarios generate progress 2 #
POST /test_framework/v1/scenarios/improve_instructions/ Scenarios improve instructions create 2 #
GET /test_framework/v1/scenarios/instructions-progress/ Scenarios instructions progress retrieve 2 #
POST /test_framework/v1/scenarios/move_folder/ Scenarios folder move 2 #
POST /test_framework/v1/scenarios/rename_folder/ Scenarios folder rename 2 #
POST /test_framework/v1/scenarios/scenario-agent/ Scenarios refine 2 #
GET /test_framework/v1/scenarios/scenario-agent-progress/ Scenarios refine progress 2 #
POST /test_framework/v1/scenarios/validate_scenarios_json/ Validate a JSON test-suite spec without running it #
GET /test_framework/v1/test-profiles/ List test profiles #
POST /test_framework/v1/test-profiles/ Create a test profile #
GET /test_framework/v1/test-profiles/{id}/ Get a test profile #
PATCH /test_framework/v1/test-profiles/{id}/ Update a test profile #
DELETE /test_framework/v1/test-profiles/{id}/ Delete a test profile #
GET /test_framework/v1/tools/ List the mock tools in a project #
GET /test_framework/v1/tools/{id}/ Get one mock tool #
GET /test_framework/v2/aiagents/ List AI voice agents #
POST /test_framework/v2/aiagents/ Create an AI voice agent #
GET /test_framework/v2/aiagents/{id}/ Retrieve an AI voice agent #
DELETE /test_framework/v2/aiagents/{id}/ Delete an AI voice agent #
POST /test_framework/v2/aiagents/{id}/auto-fetch/ Auto-fetch the agent configuration from its provider #
GET /test_framework/v2/aiagents/{id}/auto-fetch-progress/ Poll status of an auto-fetch task #
POST /test_framework/v2/aiagents/{id}/disable_personalities/ Disable personalities for an agent's project #
POST /test_framework/v2/aiagents/{id}/duplicate/ Duplicate an AI voice agent #
POST /test_framework/v2/aiagents/{id}/enable_personalities/ Enable personalities for an agent's project #
GET /test_framework/v2/aiagents/{id}/personalities/ List personalities available to an agent #
POST /test_framework/v2/aiagents/{id}/upload_knowledge_base/ Upload AI agent knowledge base #
GET /test_framework/v2/aiagents/provider-assistants/ List assistants on a connected provider account #
DELETE /test_framework/v2/metrics/{id}/ Delete a metric #
POST /test_framework/v2/metrics/{id}/run_reviews/ Run metric reviews #
POST /test_framework/v2/metrics/bulk_create/ Create multiple metrics in a single request #
POST /test_framework/v2/metrics/generate_clean_description/ Generate a clean metric description #
POST /test_framework/v2/metrics/generate_clean_description_bg/ Start async clean description generation #
GET /test_framework/v2/metrics/generate_clean_description_progress/ Poll async clean description generation #
POST /test_framework/v2/metrics/generate_evaluation_trigger/ Generate a metric evaluation trigger #
POST /test_framework/v2/metrics/generate_metrics/ Generate suggested metrics #
GET /test_framework/v2/metrics/generate_metrics_progress/ Get metric generation progress #
POST /test_framework/v2/metrics/preview/ Preview a metric #
GET /test_framework/v2/metrics/preview-progress/ Get metric preview progress #
PATCH /test_framework/v2/metrics/reorder/ Reorder project metrics #
GET /test_framework/v2/metrics/run_reviews_progress/ Get metric reviews progress #
POST /test_framework/v2/metrics/simplify_prompt/ Simplify a metric prompt #
GET /test_framework/v2/metrics/simplify_prompt_progress/ Get prompt simplification progress #
GET /test_framework/v2/results/ List test results #
GET /test_framework/v2/results/{id}/ Retrieve a test result #
POST /test_framework/v2/results/{id}/evaluate_metrics/ Evaluate metrics on a result #
POST /test_framework/v2/results/{id}/rerun/ Re-run the scenarios from a completed test result #
GET /test_framework/v2/runs/{id}/ Retrieve a test run #
GET /test_framework/v2/runs/bulk/ Get multiple runs #
GET /test_framework/v2/scenarios/ List evaluators #
GET /test_framework/v2/scenarios/{id}/ Retrieve an evaluator #
DELETE /test_framework/v2/scenarios/{id}/ Delete an evaluator #
GET /test_framework/v2/scenarios/{id}/condition-audio/ List an evaluator's audio clips #
POST /test_framework/v2/scenarios/{id}/condition-audio/ Upload an audio clip to an evaluator #
PUT /test_framework/v2/scenarios/{id}/condition-audio/{audio_id}/ Replace an audio clip's recording #
PATCH /test_framework/v2/scenarios/{id}/condition-audio/{audio_id}/ Correct an audio clip's transcript and word timings #
POST /test_framework/v2/scenarios/create-from-transcript-bg/ Create a scenario from a transcript #
GET /test_framework/v2/scenarios/create-from-transcript-progress/ Get scenario-from-transcript progress #
POST /test_framework/v2/scenarios/create_folder/ Create a folder #
POST /test_framework/v2/scenarios/delete_folder/ Delete a scenario folder #
GET /test_framework/v2/scenarios/folders/ List scenario folders #
POST /test_framework/v2/scenarios/generate-bg/ Generate scenarios in background #
POST /test_framework/v2/scenarios/generate-instructions/ Generate scenario instructions #
GET /test_framework/v2/scenarios/generate-progress/ Get scenario generation progress #
POST /test_framework/v2/scenarios/improve_instructions/ Improve scenario instructions #
GET /test_framework/v2/scenarios/instructions-progress/ Get scenario instructions progress #
POST /test_framework/v2/scenarios/move_folder/ Move a scenario folder #
POST /test_framework/v2/scenarios/rename_folder/ Rename a scenario folder #
POST /test_framework/v2/scenarios/scenario-agent/ Clarify what evaluator scenarios should cover #
GET /test_framework/v2/scenarios/scenario-agent-progress/ Get scenario-refinement progress #
POST /test_framework/v2/scenarios/validate_scenarios_json/ Validate a JSON test-suite spec without running it #
POST /test_framework/v3/aiagents/ Create agent #
POST /test_framework/v3/aiagents/{id}/auto-fetch/ Auto-fetch agent from provider #
POST /test_framework/v3/metrics/{id}/run_reviews/ Run metric reviews #
POST /test_framework/v3/metrics/generate_clean_description/ Generate clean metric description #
POST /test_framework/v3/metrics/generate_metrics/ Generate metrics #
POST /test_framework/v3/metrics/preview/ Preview metric #
POST /test_framework/v3/metrics/simplify_prompt/ Simplify metric prompt with AI #
POST /test_framework/v3/results/{id}/ask_about_failures/ Ask about failed runs #
POST /test_framework/v3/scenarios/create-from-transcript/ Create evaluator from transcript #
POST /test_framework/v3/scenarios/generate/ Generate evaluator #
POST /test_framework/v3/scenarios/generate-instructions/ Generate scenario instructions with AI #
POST /test_framework/v3/scenarios/improve_instructions/ Improve scenario instructions with AI #

Specifications

⚙
OpenAPI
https://artifacts.apis.io/cekura-ai/openapi/cekura-ai-test-framework-api-openapi.yml

Schemas & Data

📊
JSONSchema
https://artifacts.apis.io/cekura-ai/json-schema/cekura-ai-project-schema.json
📊
JSONSchema
https://artifacts.apis.io/cekura-ai/json-schema/cekura-ai-patched-project-schema.json
📊
JSONSchema
https://artifacts.apis.io/cekura-ai/json-schema/cekura-ai-organization-schema.json
📊
JSONSchema
https://artifacts.apis.io/cekura-ai/json-schema/cekura-ai-result-detail-v2-schema.json
📊
JSONSchema
https://artifacts.apis.io/cekura-ai/json-schema/cekura-ai-schema-combined-results-report-schema.json
📊
JSONSchema
https://artifacts.apis.io/cekura-ai/json-schema/cekura-ai-schema-scenario-schema.json

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/cekura-ai:cekura-ai-test-framework-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

cekura-ai-test-framework-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: Cekura Test Framework API
  version: v1
  description: Complete API documentation for the Cekura platform. This API provides endpoints for testing, observing, and evaluating AI voice agents — including managing agents, running evaluators, defining metrics, and analyzing call quality.
servers:
- url: https://api.cekura.ai
tags:


# --- truncated at 32 KB (566 KB total) ---
# Full source: https://artifacts.apis.io/cekura-ai/openapi/cekura-ai-test-framework-api-openapi.yml