> ## Documentation Index > Fetch the complete documentation index at: https://deepline.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Use Podscan in Deepline > Use Podscan to find every podcast episode where a keyword, brand, competitor, or topic is discussed, and to pull host/guest metadata and topic sentiment from. [Human guide: work with your agent →](https://deepline.com/docs/human/providers/podscan/guide.md) Inspect one Podscan action before starting provider-backed work. Your first result is a verified input and output contract. ## Provider-specific requirements Podscan indexes and transcribes the podcast ecosystem and exposes full-text search across every transcript. ### When to use * "Find every podcast where {topic / brand / competitor} was discussed." * "Who talked about {subject} on a podcast?" — episode transcripts carry structured host/guest metadata (name, company, occupation, industry). * Social-listening / brand-monitoring over spoken audio, not just text. * Sourcing warm outbound targets: podcast guests who discussed your category are high-intent, self-identified buyers. ### Operations * `podscan_episodes_search` — full-text transcript search. Returns matching episodes with the matched `_search_highlight` snippet, the parent `podcast`, `metadata.hosts[]` / `metadata.guests[]` (name + company + occupation), and AI-extracted `topics[]` with sentiment. Use quoted phrases for precision, e.g. `"customer interviews"`. Full transcripts are omitted by default (they are large). pass `include_transcript: true` only when you need them. * `podscan_podcasts_search` — discover shows by title/description. ### Tips * Quote multi-word phrases to avoid loose matches. * `pagination.total` gives the corpus-wide mention count for a query — useful for sizing before pulling pages. * `language` filters by ISO 639-1 code (e.g. `en`) and is honored by the API. Date and category filtering are not currently exposed because Podscan's documented search surface does not reliably support them. * Turn guests into contactable leads by piping `guest_name` + `guest_company` into LinkedIn resolution and an email waterfall. ### Auth & billing Deepline supplies the Podscan credential (`PODSCAN_API_KEY`). Billing applies per successful search — a well-formed response with at least one result. Zero-match searches are free. A malformed provider response is rejected rather than billed as an empty result. Deepline credit pricing for these actions is generated from the provider pricing metadata and rendered on the public provider pages. ### Rate limits Podscan rate-limits aggressively (roughly 10 req/min on trial plans, higher on paid). The connector applies a conservative shared limit and surfaces upstream 429s. For multi-query or paginated work, call the tools through `ctx.tools.execute({ id, tool, input, description })` inside a Play so Deepline owns provider pacing and retries. Run an authorized local workflow with `deepline plays run --file podcast-research.play.ts --input '{"query":"customer interviews"}' --watch` after authoring it with that input contract. A supplied Play needs no extra pilot run. Use `deepline runs get ` to inspect existing results, not a fresh search or paid repair. Do not bypass provider limits with an external loop. ## Find an applicable action Confirm your effective workspace, then search the live catalog: ```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}} deepline auth status --json deepline search "Podscan" --type tools --json ``` Search returns candidates. Check the returned provider and operation rather than selecting a similar title automatically. ## Inspect the selected contract Replace `` with the identifier returned by discovery: ```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}} deepline describe --json ``` These commands do not execute the selected provider action. Read its required inputs, supported access mode, pricing unit, outputs, and limits. A connection does not establish that every action supports BYOK. Follow the provider-specific requirements above and the live action contract. ## Prepare one reviewed input Use one authorized record that matches the inspected schema. Preserve its source identity and define the result you will accept. Open the action reference for its payload and response shape. Provider-backed execution can incur usage or external effects. For reusable logic, follow [Write Plays](https://deepline.com/docs/sdk-v2/plays.md). For direct-call recovery, use [Tool execution recovery](https://deepline.com/docs/sdk-v2/tool-execution-recovery.md). > [!TIP] > > Continue only when the workspace, provider, required fields, acceptance rule, and applicable price are understood. Keep unavailable access separate from no-result evidence. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.