Castingwords for AI agents
CastingWords offers human-powered transcription, converting recorded audio into accurate text through a straightforward API rather than automated speech recognition alone. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Castingwords.
Order a transcript
Order a transcript for a recorded audio file, ready to receive once transcribers finish it.
Check a transcript's progress
Check the account's prepay balance before ordering another batch of audio transcripts.
Confirm before canceling an order
Cancel and refund an audio file's order before transcription work has started on it.
9 Castingwords actions, graded by risk.
Every Castingwords action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- castingwords.get_webhookGet registered webhook URL
- castingwords.get_transcriptGet Transcript
- castingwords.get_prepay_balanceGet Prepay Balance
- castingwords.test_webhookTest Webhook Call
write
4Create and change things. Allow, or ask the user first.
- castingwords.sku_listList Available SKUs
- castingwords.order_upgradesOrder Upgrades
- castingwords.order_transcriptOrder Transcript
- castingwords.register_webhookRegister Webhook
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- castingwords.cancel_audiofileCancel and Refund Audio File
Castingwords in three steps.
- 01Your users connect CastingwordsThey add their Castingwords api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “list Available SKUs” can wait for the user, and “cancel and Refund Audio File” can be denied outright.
- 03Any agent can actYour agent calls Castingwords through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('castingwords', { read: 'allow', write: 'ask', // sku_list destructive: 'deny', // cancel_audiofile }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Castingwords connects.
Users add their Castingwords api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Castingwords connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Castingwords from any agent.
Castingwords and Arc0, answered.
Can I use Castingwords with Claude, ChatGPT or Cursor?
Yes. Connect Castingwords to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Castingwords actions you allow.
How do users connect Castingwords?
Users add their Castingwords api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Castingwords actions can my agent take?
9 in total: 4 read, 4 write and 1 destructive, such as “list Available SKUs”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Castingwords?
Yes. Actions like “cancel and Refund Audio File” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Castingwords too?
Yes. The same Castingwords connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Castingwords into your agent.
Your users connect Castingwords once, under your brand. Your agent gets 9 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan