Audio & Podcast Search Pipeline

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY")

namespace = client.namespaces.create(name="audio-search")
collection = client.collections.create(
    namespace_id=namespace.id,
    name="podcasts",
    extractors=["audio-transcription", "text-embedding-v2"],
    chunk_strategy="speaker-turn"
)

# Upload audio files
client.buckets.upload(
    collection_id=collection.id,
    url="s3://your-bucket/podcasts/"
)

# Search across all episodes
results = client.retrievers.execute(
    retriever_id=retriever.id,
    query="discussion about AI regulation in Europe"
)