Exa · Podcast transcript search with speakers and timestamps
Particle
Particle data through the Exa Agent: search 100,000+ transcribed podcasts; each hit is a speaker-attributed transcript window with timestamps, show and episode metadata. Ask in natural language and, for structured output, pass output_schema naming the fields you want from Particle. Examples: "What podcast hosts said about AI regulation in the last month: show, speaker, quote, timestamp, stance." "Recent podcast mentions of Anthropic with speaker-attributed quotes." Price: Exa effort (minimal $0.012, low $0.025, medium $0.10, high $0.50 per run) plus $0.015 per Particle call; the cost Exa reports is billed, up to max_cost_usd (default $0.25). Usually answers inline within a minute; otherwise returns a run id to read with exa/agent-run-get.
Usage based ExaNewsexa/particleListed
Activation pending; your agent will see it as unavailable until then.
Use this tool with your agent
Use my connected Agentik MCP server. I want to use the tool exa/particle (Particle via Exa: podcast transcript search with speakers and timestamps). Call inspect_tool with {"tool_id": "exa/particle"} first and tell me the price before anything runs. Ask me for the inputs it needs; never invent values, IDs or file URLs. When I confirm, call run_tool with tool_id "exa/particle" and my inputs, follow it with get_run if it is still running, and give me the result and the price Agentik reports. If the tool is unavailable, say so and use discover_tools to propose an alternative.Show the prompt
Paste it into Claude, ChatGPT or Codex: your agent takes it from there, and shows the price before it runs.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
query | string | Yes | What you want from Particle, in natural language. Be explicit about the entities (domains, tickers, company names, routes, dates) and the fields you expect. |
output_schema | object | No | Optional JSON Schema for the structured answer (returned in output.structured). Name each field after the Particle data you want, e.g. {"type":"object","required":["domain","monthlyVisits"],"properties":{"domain":{"type":"string"},"monthlyVisits":{"type":"number","description":"from Particle"}}}. |
effort | string | No | Exa Agent effort: minimal $0.012 (one quick lookup), low $0.025 (default), medium $0.10, high $0.50, plus partner calls. Options: minimal, low, medium, high. |
max_cost_usd | number | No | Ceiling reserved for this run, effort plus Particle calls (default $0.25, at most $5). The real cost Exa reports is billed, never more than this. |
How your agent calls it
First inspect_tool for the current schema and price, then run_tool with the published example after confirming your inputs:
{
"tool_id": "exa/particle",
"input": {
"query": "One recent podcast quote mentioning Anthropic, with show and speaker, from Particle.",
"effort": "minimal"
}
}Price and billing
- Price
- Usage based
- Model
- Usage based
- Detail
- Billed at the cost the provider reports for the call, never above $5. Your agent sees the maximum before running.
- The provider’s price, 0% markup.
- One prepaid balance for every provider; your agent sees the price before it runs.
- Pay for measured usage; unused reservations are released.