NEWVectors or files. Pick a path.Start →
    media

    Audio
    Chapters
    Converter

    Automatically segment audio recordings into topic-based chapters with titles, timestamps, and summaries. Uses speech transcription combined with topic modeling to detect natural topic boundaries in podcasts, lectures, meetings, and audiobooks.

    Max file size: 2 GB
    Estimated: 2-8 min per hour of audio
    5 input formats

    How It Works

    1

    Upload an audio file or provide a URL to the Mixpeek API.

    2

    The audio is transcribed with speaker diarization and sentence-level timestamps.

    3

    Topic modeling identifies semantic shift points where the subject matter changes.

    4

    An LLM generates a descriptive title and brief summary for each detected chapter.

    5

    Chapters are returned with start/end timestamps, titles, and summaries.

    Code Examples

    import os, requests
    
    API = "https://api.mixpeek.com"
    H = {"Authorization": f"Bearer {os.environ['MIXPEEK_API_KEY']}",
         "X-Namespace": os.environ["NAMESPACE_ID"]}
    
    # 1. a bucket, with a schema that declares the field you will send
    bucket = requests.post(f"{API}/v1/buckets", headers=H, json={
        "bucket_name": "audio-inputs",
        "bucket_schema": {"properties": {"audio": {"type": "audio"}}},
    }).json()
    
    # 2. land the file as an object. the URL goes in data, on the blob
    requests.post(f"{API}/v1/buckets/{bucket['bucket_id']}/objects", headers=H, json={
        "key_prefix": "run-1",
        "blobs": [{"property": "audio", "type": "audio",
                   "data": "https://example.com/call.mp3"}],
    })
    
    # 3. a collection over that bucket, running the extractor
    collection = requests.post(f"{API}/v1/collections", headers=H, json={
        "collection_name": "audio-to-chapters",
        "source": {"type": "bucket", "bucket_ids": [bucket["bucket_id"]]},
        "feature_extractor": {"feature_extractor_name": "multimodal_extractor", "version": "v1"},
    }).json()
    
    # 4. run extraction over the bucket
    requests.post(f"{API}/v1/buckets/{bucket['bucket_id']}/batches", headers=H, json={
        "collection_ids": [collection["collection_id"]],
        "auto_submit": True,
    })
    
    # 5. read the output
    docs = requests.get(
        f"{API}/v1/collections/{collection['collection_id']}/documents", headers=H
    ).json()
    print(docs)

    Use Cases

    Generate chapter markers for podcast episodes on Apple Podcasts and Spotify
    Create navigable table-of-contents for recorded lectures and webinars
    Segment long audiobooks into listenable chapters
    Build topic-based indexes for meeting recording archives

    Supported Input Formats

    MP3
    WAV
    FLAC
    OGG
    AAC

    Quick Info

    Categorymedia
    Max File Size2 GB
    Est. Time2-8 min per hour of audio

    Processing millions of files?

    Run this as a managed pipeline over your whole library, no infrastructure to build or maintain. Talk to us about processing at scale.

    Run it over a library

    Mixpeek runs this conversion as a pipeline over a whole library in your object storage, with the output landing as queryable documents. It is not a single-file converter.

    Frequently Asked Questions

    Ready to convert audio to chapters?

    Start using the Mixpeek Audio to Chapters in minutes. Sign up for a free API key and follow the documentation to get started.