CastingWords MCP integration for AI agents.
Connect AI agents to CastingWords through 4 structured actions, including get prepay balance, submit transcription, and get transcript. Review authentication…
- ACTION CONTRACTS
- 4
- 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 CastingWords integration exposes
The CastingWords Agent App exposes 4 provider-backed actions for design & media and productivity work. Its current contract lets an authorized agent get the current castingwords prepay balance in us dollars, submit one publicly accessible audio or video url for asynchronous human transcription, and retrieve a completed castingwords transcript as plain text or html. 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 CastingWords account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real CastingWords capabilities.
Showing 4 of 4 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_prepay_balanceREADGet the current CastingWords prepay balance in US dollars.
submit_transcriptionREVIEWSubmit one publicly accessible audio or video URL for asynchronous human transcription.
INPUTS: mediaUrl / serviceTier / addons / speakerNames / notes
get_transcriptREADRetrieve a completed CastingWords transcript as plain text or HTML.
INPUTS: audiofileId / format / test
get_transcription_statusREADGet the current CastingWords processing state and documented audio file details.
INPUTS: audiofileId
INPUT CONTRACTS
Know what the action needs before it runs.
submit_transcription
mediaUrlREQUIRED- A directly downloadable public audio or video URL that CastingWords should transcribe.
serviceTierREQUIRED- The transcription tier: TRANS14 for Budget, TRANS2 for 1-Day, or TRANS6/TRANS7 for 7-Day service.
addonsOPTIONAL- Optional add-on SKUs applied to the transcription.
speakerNamesOPTIONAL- Speaker names that help transcribers identify people in the recording.
notesOPTIONAL- Instructions or context for the transcribers.
get_transcript
audiofileIdREQUIRED- The CastingWords audio file identifier.
formatOPTIONAL- The requested text transcript format. Defaults to txt.
testOPTIONAL- Whether to request the official fake transcript response for supported test audio file IDs.
get_transcription_status
audiofileIdREQUIRED- The CastingWords audio file identifier.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Prepay Balance
Get the current CastingWords prepay balance in US dollars. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_prepay_balanceVerify with Get Transcript
Retrieve a completed CastingWords transcript as plain text or HTML. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_transcriptSAFETY BOUNDARY
Operate CastingWords with explicit limits
- Authorize CastingWords with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned CastingWords data may still be sensitive and should be minimized before it enters model context.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in CastingWords rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the CastingWords task completed successfully.
CONNECTION MODEL
API key
CastingWords API key used to order and retrieve transcriptions. Sign in and copy the API key from your account settings: https://castingwords.com/customer/info.
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
- 0
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 1
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 CastingWords.