Build a conversation-intelligence feature

import crypto from "node:crypto";

app.post("/webhooks/transcription", async (req, reply) => {
  const raw = req.rawBody; // the exact bytes we signed
  const expected = crypto
    .createHmac("sha256", process.env.PYAI_WEBHOOK_SECRET!)
    .update(raw)
    .digest("hex");
  const got = req.headers["x-pyai-signature"];
  if (!got || !crypto.timingSafeEqual(Buffer.from(got), Buffer.from(expected))) {
    return reply.code(401).send();
  }

  const { job_id } = JSON.parse(raw);
  const job = await pyai.transcriptionJobs.get(job_id); // fetch authoritative result
  await analyzeCall(job);
  reply.code(200).send();
});

import requests

def load_result(job):
    if getattr(job, "result_url", None):
        return requests.get(job.result_url, timeout=30).json()
    return job.result

result = load_result(job)
print(result["speakers"], "speakers,", result["audio_seconds"], "s of audio")

# SRT/VTT are signed URLs in result["formats"]
srt_url = result["formats"]["srt"]
open("call.srt", "wb").write(requests.get(srt_url, timeout=30).content)

from collections import defaultdict

def speaker_key(seg):
    # stereo → channel (0/1); mono diarization → "speaker_0" etc.
    return f"ch{seg['channel']}" if "channel" in seg else seg.get("speaker", "unknown")

def talk_ratio(segments):
    secs = defaultdict(float)
    for s in segments:
        secs[speaker_key(s)] += s["end"] - s["start"]
    total = sum(secs.values()) or 1.0
    return {k: round(v / total, 3) for k, v in secs.items()}

def track_keywords(segments, terms):
    hits = defaultdict(list)
    for s in segments:
        low = s["text"].lower()
        for term in terms:
            if term.lower() in low:
                hits[term].append({"at": s["start"], "speaker": speaker_key(s)})
    return hits

segments = result["segments"]
ratios = talk_ratio(segments)          # {"ch0": 0.62, "ch1": 0.38}
keywords = track_keywords(segments, ["pricing", "competitor", "contract", "discount"])

from openai import OpenAI  # works against any OpenAI-compatible endpoint

# ↓↓↓ Your LLM of choice — not a PyAI endpoint ↓↓↓
llm = OpenAI(base_url=os.environ["LLM_BASE_URL"], api_key=os.environ["LLM_API_KEY"])

def labeled_transcript(segments):
    return "\n".join(f"[{speaker_key(s)}] {s['text']}" for s in segments)

def summarize(segments, ratios):
    resp = llm.chat.completions.create(
        model="your-model",
        messages=[
            {"role": "system", "content":
             "You are a sales-call analyst. Return a 3-sentence summary, "
             "a bulleted list of action items, and the customer's sentiment."},
            {"role": "user", "content":
             f"Talk-ratio: {ratios}\n\nTranscript:\n{labeled_transcript(segments)}"},
        ],
    )
    return resp.choices[0].message.content

insights = summarize(segments, ratios)