Video chapters with Llama and Ittybit

const res = await fetch("https://api.ittybit.com/jobs", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ITTYBIT_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    input: "https://example.com/uploads/talk.mp4",
    kind: "audio",
    options: { format: "mp3" },
  }),
});
const task = await res.json();

import requests
import os

res = requests.post(
    "https://api.ittybit.com/jobs",
    headers={"Authorization": f"Bearer {os.environ['ITTYBIT_API_KEY']}"},
    json={
        "input": "https://example.com/uploads/talk.mp4",
        "kind": "audio",
        "options": {"format": "mp3"},
    },
)
task = res.json()

import { execSync } from "child_process";
import { readFileSync } from "fs";

// Download the extracted audio
const audioUrl = task.output.url;
const audioRes = await fetch(audioUrl);
const audioBuffer = Buffer.from(await audioRes.arrayBuffer());
const fs = await import("fs");
fs.writeFileSync("/tmp/audio.mp3", audioBuffer);

// Transcribe with whisper.cpp
execSync(
`./whisper-cpp -m models/ggml-base.en.bin -f /tmp/audio.mp3 --output-json -of /tmp/transcript`
);

const transcript = JSON.parse(
readFileSync("/tmp/transcript.json", "utf-8")
);

// Build a timestamped transcript string
const lines = transcript.transcription.map(
(seg: { offsets: { from: number }; text: string }) => {
const seconds = Math.floor(seg.offsets.from / 1000);
const mm = String(Math.floor(seconds / 60)).padStart(2, "0");
const ss = String(seconds % 60).padStart(2, "0");
return `[${mm}:${ss}] ${seg.text.trim()}`;
}
);
const timestampedTranscript = lines.join("\n");

import subprocess
import json

# Download the extracted audio
audio_url = task["output"]["url"]
audio_bytes = requests.get(audio_url).content
with open("/tmp/audio.mp3", "wb") as f:
    f.write(audio_bytes)

# Transcribe with whisper.cpp
subprocess.run([
    "./whisper-cpp",
    "-m", "models/ggml-base.en.bin",
    "-f", "/tmp/audio.mp3",
    "--output-json",
    "-of", "/tmp/transcript",
], check=True)

with open("/tmp/transcript.json") as f:
    transcript = json.load(f)

# Build a timestamped transcript string
lines = []
for seg in transcript["transcription"]:
    seconds = seg["offsets"]["from"] // 1000
    mm = str(seconds // 60).zfill(2)
    ss = str(seconds % 60).zfill(2)
    lines.append(f"[{mm}:{ss}] {seg['text'].strip()}")

timestamped_transcript = "\n".join(lines)

const OLLAMA_URL = "http://localhost:11434/api/chat";

const res = await fetch(OLLAMA_URL, {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
model: "llama3.3",
stream: false,
messages: [
{
role: "system",
content: `You are a video editor. Given a timestamped transcript, produce chapter markers.

Return JSON only — an array of objects with these fields:

- "timestamp": start time as "MM:SS"
- "title": short chapter title (max 60 chars)
- "summary": one-sentence description of the chapter

Identify natural topic shifts. Aim for 4-8 chapters depending on length. Do not invent content not present in the transcript.`,
},
{
role: "user",
content: timestampedTranscript,
},
],
}),
});

const data = await res.json();
const chapters = JSON.parse(data.message.content);

console.log(chapters);

OLLAMA_URL = "http://localhost:11434/api/chat"

res = requests.post(OLLAMA_URL, json={
    "model": "llama3.3",
    "stream": False,
    "messages": [
        {
            "role": "system",
            "content": (
                "You are a video editor. Given a timestamped transcript, produce chapter markers.\n\n"
                "Return JSON only — an array of objects with these fields:\n"
                '- "timestamp": start time as "MM:SS"\n'
                '- "title": short chapter title (max 60 chars)\n'
                '- "summary": one-sentence description of the chapter\n\n'
                "Identify natural topic shifts. Aim for 4-8 chapters depending on length. "
                "Do not invent content not present in the transcript."
            ),
        },
        {
            "role": "user",
            "content": timestamped_transcript,
        },
    ],
})

chapters = json.loads(res.json()["message"]["content"])

print(chapters)

async function generateChapters(videoUrl: string) {
  // 1. Extract audio via Ittybit
  const taskRes = await fetch("https://api.ittybit.com/jobs", {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.ITTYBIT_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      input: videoUrl,
      kind: "audio",
      options: { format: "mp3" },
    }),
  });
  const task = await taskRes.json();

// 2. Poll until audio is ready
const audioUrl = await pollForResult(task.id);

// 3. Download and transcribe locally
const audioRes = await fetch(audioUrl);
const buffer = Buffer.from(await audioRes.arrayBuffer());
const { writeFileSync, readFileSync } = await import("fs");
const { execSync } = await import("child_process");

writeFileSync("/tmp/audio.mp3", buffer);
execSync(
`./whisper-cpp -m models/ggml-base.en.bin -f /tmp/audio.mp3 --output-json -of /tmp/transcript`
);

const transcript = JSON.parse(readFileSync("/tmp/transcript.json", "utf-8"));
const lines = transcript.transcription.map(
(seg: { offsets: { from: number }; text: string }) => {
const seconds = Math.floor(seg.offsets.from / 1000);
const mm = String(Math.floor(seconds / 60)).padStart(2, "0");
const ss = String(seconds % 60).padStart(2, "0");
return `[${mm}:${ss}] ${seg.text.trim()}`;
}
);

// 4. Generate chapters with Llama
const llamaRes = await fetch("http://localhost:11434/api/chat", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
model: "llama3.3",
stream: false,
messages: [
{
role: "system",
content: `You are a video editor. Given a timestamped transcript, produce chapter markers.

Return JSON only — an array of objects with these fields:

- "timestamp": start time as "MM:SS"
- "title": short chapter title (max 60 chars)
- "summary": one-sentence description of the chapter

Identify natural topic shifts. Aim for 4-8 chapters depending on length. Do not invent content not present in the transcript.`,
},
{ role: "user", content: lines.join("\n") },
],
}),
});

const data = await llamaRes.json();
return JSON.parse(data.message.content);
}

def generate_chapters(video_url: str) -> list[dict]:
    # 1. Extract audio via Ittybit
    task = requests.post(
        "https://api.ittybit.com/jobs",
        headers={"Authorization": f"Bearer {os.environ['ITTYBIT_API_KEY']}"},
        json={
            "input": video_url,
            "kind": "audio",
            "options": {"format": "mp3"},
        },
    ).json()

    # 2. Poll until audio is ready
    audio_url = poll_for_result(task["id"])

    # 3. Download and transcribe locally
    audio_bytes = requests.get(audio_url).content
    with open("/tmp/audio.mp3", "wb") as f:
        f.write(audio_bytes)

    subprocess.run([
        "./whisper-cpp",
        "-m", "models/ggml-base.en.bin",
        "-f", "/tmp/audio.mp3",
        "--output-json",
        "-of", "/tmp/transcript",
    ], check=True)

    with open("/tmp/transcript.json") as f:
        transcript = json.load(f)

    lines = []
    for seg in transcript["transcription"]:
        seconds = seg["offsets"]["from"] // 1000
        mm = str(seconds // 60).zfill(2)
        ss = str(seconds % 60).zfill(2)
        lines.append(f"[{mm}:{ss}] {seg['text'].strip()}")

    # 4. Generate chapters with Llama
    res = requests.post("http://localhost:11434/api/chat", json={
        "model": "llama3.3",
        "stream": False,
        "messages": [
            {
                "role": "system",
                "content": (
                    "You are a video editor. Given a timestamped transcript, produce chapter markers.\n\n"
                    "Return JSON only — an array of objects with these fields:\n"
                    '- "timestamp": start time as "MM:SS"\n'
                    '- "title": short chapter title (max 60 chars)\n'
                    '- "summary": one-sentence description of the chapter\n\n'
                    "Identify natural topic shifts. Aim for 4-8 chapters depending on length. "
                    "Do not invent content not present in the transcript."
                ),
            },
            {"role": "user", "content": "\n".join(lines)},
        ],
    })

    return json.loads(res.json()["message"]["content"])