How to Use Particle podcast dialogue search in opencode
Returns matching episode segments with transcript windows and overlapping highlights. Use it to find discussions by meaning or exact wording, rather than collecting every mention of one company.
Prompts to try with Particle podcast dialogue search in opencode
Copy an example into opencode, or ask in your own words.
Use Particle podcast dialogue search to find discussions about vector databases and render selected matching passages in our research view.
Use Particle podcast dialogue search to look this up and give me the result as a table. Save the result in ./assets.
Pull the latest numbers from Particle podcast dialogue search and tell me what changed since last week.
Check Particle podcast dialogue search and summarize what you find in three bullet points.
Pull the newest data from Particle podcast dialogue search and give me the result as a table.
How to set up Particle podcast dialogue search in opencode
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
- Sign in
Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.
opencode mcp auth spiral
- Check it
Spiral shows as connected.
opencode mcp list
Use the Spiral skill
- Send opencode this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Particle podcast dialogue search
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "alexandria", "model": "particle/podcasts/episodes/search", "input": { "semantic_search": "<semantic_search>" } }'
Then paste one of the prompts above: opencode finds Particle podcast dialogue search on Spiral, shows the price and runs it.
Particle podcast dialogue search providers and prices
Spiral runs Particle podcast dialogue search through Alexandria. Open a card for today's price, with every fee included.
Settings you can ask for
Ask opencode for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Role | guest, host, panelist, correspondent, speaker, or mention | How the entity must relate to the episode: a speaking role, speaker for any speaking role, or mention for being talked about. | |
| Sort | relevance or recency | relevance (default) or recency. | |
| Type | INTRO, PERSONAL_BANTER, TOPIC_DISCUSSION, INTERVIEW, TRANSITION, AD, or OUTRO | Only segments of this type. | |
| Limit | 1 to 100 | 25 | Maximum records to return. |
| Context | 1 to 15 | 1 | Lines of surrounding dialogue around each matched line. Widen this instead of fetching the transcript. |
| Keyword match | required or ranked | required | How unquoted keyword terms apply: required filters to segments containing every term (and constrains a hybrid query to their intersection); ranked lets them only boost. |
Every API field of Particle · Episode search is on its tool page: open its card above.
What can you do with Particle podcast dialogue search in opencode?
Build a podcast research view that connects show identities, episode records, dialogue, and publisher context. Use Particle data to populate the project's research screens and distinguish newly processed material from historical publication activity.
Prepare a topic desk briefing
Build a climate-policy show shortlist, inspect relevant episodes and publishers, follow newly processed releases, and compare episode volume with matching discussions.
Review a company's public podcast coverage
For a company such as NVIDIA, find relevant episodes, read the surrounding discussion, compare mention volume, and identify the publishers behind the coverage.
Research an archived news story
Start with known show or episode links, locate discussions of a past event, and compare episode and company-mention patterns around its dates.
Plan an evidence-based editorial calendar
Find relevant shows, inspect discussions about semiconductor manufacturing, and compare episode activity with company-mention patterns before choosing follow-up topics.
More on Particle podcast dialogue search and opencode
Overview
Particle podcast dialogue search in other agents
Questions about Particle podcast dialogue search in opencode
Can opencode use Particle podcast dialogue search?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Particle podcast dialogue search like any built-in tool.
How much does Particle podcast dialogue search cost in opencode?
$0.026189 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.
Do I need an Alexandria account to use Particle podcast dialogue search in opencode?
No. Spiral runs Particle podcast dialogue search on its own Alexandria account. You sign in to Spiral once and never paste a key.
How long does it take to set up Particle podcast dialogue search in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while Particle podcast dialogue search runs?
Particle podcast dialogue search runs in the background. opencode starts the run, checks on it and gives you the json when it's ready.
Does Particle cover every podcast?
Particle describes coverage of the Apple Podcasts Top 200 across more than 130 English-language verticals, plus independent shows. That coverage statement does not establish complete coverage of every podcast or language.
How quickly does new podcast data appear?
Every tracked show's feed is checked at least every two days. After discovery, transcription and enrichment take minutes to hours, so publication and searchable availability can differ.
How far back does the data go?
Particle's transcribed episode history reaches back to 2017. Coverage varies by show, and an older episode discovered in a feed may still lack a transcript.
Does an episode record guarantee that its dialogue is searchable?
No. Particle also holds discovered episodes without transcripts; those records have no transcript-derived speakers, entities, segments, or clips.
Will following new episodes also retrieve a show's complete archive?
No. Particle excludes bulk historical imports from its episode feed, while keeping those episodes available through search and episode listings.
Start using Particle podcast dialogue search in opencode
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into opencode:
set up https://spiral.ai/SKILL.md


