> ## Documentation Index
> Fetch the complete documentation index at: https://docs.goparlay.io/llms.txt
> Use this file to discover all available pages before exploring further.
# Quickstart
> Submit your first analysis in 5 minutes — REST or MCP, your pick.
Pick your path.
## 1. Get a sandbox key
Email your point of contact at Parlay or use the [signup form](https://console.goparlay.io/signup). You'll receive a key prefixed `pk_sandbox_…`.
## 2. Submit a mock analysis
Mock fixture URLs are deterministic test data. Free, instant, no real audio required.
```bash cURL theme={null}
curl -X POST https://api.goparlay.io/v1/analyses \
-H "Authorization: Bearer pk_sandbox_YOUR_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"org_id": "demo-acme",
"rep_id": "alex-smith",
"recording_url": "mock://perfect-pitch"
}'
```
```javascript Node.js theme={null}
const res = await fetch("https://api.goparlay.io/v1/analyses", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.PARLAY_API_KEY}`,
"Content-Type": "application/json",
"Idempotency-Key": crypto.randomUUID(),
},
body: JSON.stringify({
org_id: "demo-acme",
rep_id: "alex-smith",
recording_url: "mock://perfect-pitch",
}),
});
const job = await res.json();
console.log(job.id); // → "f2782fc7-5355-48bf-a314-d6bf90bc4907"
```
```python Python theme={null}
import os, uuid, requests
res = requests.post(
"https://api.goparlay.io/v1/analyses",
headers={
"Authorization": f"Bearer {os.environ['PARLAY_API_KEY']}",
"Idempotency-Key": str(uuid.uuid4()),
},
json={
"org_id": "demo-acme",
"rep_id": "alex-smith",
"recording_url": "mock://perfect-pitch",
},
)
job = res.json()
print(job["id"])
```
You get back a 202 with `{ id, status: "queued", created_at }`.
## 3. Poll until complete
```bash theme={null}
curl https://api.goparlay.io/v1/analyses/ \
-H "Authorization: Bearer pk_sandbox_YOUR_KEY"
```
`status` will be `queued` → `processing` → `completed`. Mock fixtures usually complete in under a second; real audio takes 30–90 seconds. The full analysis JSON sits in the `analysis` field once `status === "completed"`.
Production integrations should use webhooks instead of polling. See the [webhooks guide](/guides/webhooks).
## 4. Read the result
A completed analysis returns this canonical shape under the `analysis` field. Six pillars (clarity, influence, objection, discovery, delivery, close), each 0–100, plus a computed `overall_score` and KPIs flat at the top:
```json theme={null}
{
"id": "ec1851ba-4037-41bf-9ad5-d64391c11ab4",
"status": "completed",
"duration_seconds": 312,
"transcript": { "utterances": [ /* ... */ ], "word_count": 22 },
"analysis": {
"prospect_name": "Casey Morgan",
"recording_title": "Closed Casey",
"double_down": "The pacing on the value prop was perfect — keep doing exactly that.",
"ai_summary": "Strong opening, clean discovery, textbook objection handling, confident close.",
"ai_summary_v5": "Strong opening, clean discovery, textbook objection handling, confident close.",
// KPIs (flat, no wrapper)
"questions_asked": 11,
"filler_word_count": 3,
"words_per_minute": 142,
// Six-pillar scores (flat, _score suffix) + computed overall
"overall_score": 95,
"clarity_score": 94,
"influence_score": 96,
"objection_score": 92,
"discovery_score": 95,
"delivery_score": 97,
"close_score": 96,
// Per-pillar feedback (nested under _v5)
"feedback_v5": {
"clarity": { "positive": "...", "negative": "..." },
"influence": { "positive": "...", "negative": "..." },
"objection": { "positive": "...", "negative": "..." },
"discovery": { "positive": "...", "negative": "..." },
"delivery": { "positive": "...", "negative": "..." },
"close": { "positive": "...", "negative": "..." }
},
// Action plan (3 named sections, also under _v5)
"action_plan_v5": {
"double_down_implementation": "...",
"general_communication_improvement": "...",
"quoted_principle": "..."
},
"organization_prompt_summary": null,
"organization_feedback": null,
"master_prompt_id": null,
"master_prompt_version": "v5",
"persona_snapshot": null,
"synthesis_snapshot": null
}
}
```
The shape is identical for `mock://*` fixtures and real audio. Build your decoder once against `mock://perfect-pitch`, ship with confidence.
## 5. Real audio
Replace `mock://perfect-pitch` with a publicly reachable HTTPS URL to an MP3, WAV, M4A, or FLAC file. Pre-signed S3 / GCS URLs are fine. The file must not require additional auth headers.
## 1. Get a sandbox key
Email your point of contact at Parlay or use the [signup form](https://console.goparlay.io/signup).
## 2. Add Parlay to your AI client
```json Claude Desktop theme={null}
{
"mcpServers": {
"parlay": {
"command": "npx",
"args": ["-y", "@goparlay/mcp-server@latest"],
"env": {
"PARLAY_API_KEY": "pk_sandbox_YOUR_KEY"
}
}
}
}
```
```json Cursor theme={null}
{
"mcpServers": {
"parlay": {
"command": "npx",
"args": ["-y", "@goparlay/mcp-server@latest"],
"env": { "PARLAY_API_KEY": "pk_sandbox_YOUR_KEY" }
}
}
}
```
```bash Claude Code (CLI) theme={null}
claude mcp add parlay -e PARLAY_API_KEY=pk_sandbox_YOUR_KEY -- npx -y @goparlay/mcp-server@latest
```
Restart your client. Parlay's tools appear in the tool picker.
See the full [installation guide](/mcp/installation) for Windsurf, Continue, Zed, Claude Code, and custom SDK setups.
## 3. Try it
Paste this into a fresh conversation:
```
Use parlay tools — submit mock://perfect-pitch for analysis under org "demo-acme" rep "alex-smith". Wait for the result and tell me Alex's overall score.
```
The model will call `analyze_recording`, poll until complete, and report back the score. \~10 seconds end to end for mock fixtures.
## 4. Go further
```
Now ask Scout what Alex's biggest improvement area is on that call.
```
```
Generate a coaching synthesis for Alex using that analysis.
```
```
What sales personas does Parlay recognize?
```
## You're integrated. What's next?
Submit your own recordings, configure org defaults
Stop polling — get notified when analyses complete
Turn call notes into structured playbooks
Persona, methodology, and synthesis at scale