Skip to content

Home

Requirements

Python versions 3.8 and 3.9 are supported

Installation

Basic installation:

pip install hume

Websocket and streaming features can be enabled with:

pip install hume[stream]

Basic Usage

Submit a new batch job

Note: Your personal API key can be found in the profile section of beta.hume.ai

from hume import HumeBatchClient
from hume.models.config import FaceConfig

client = HumeBatchClient("<your-api-key>")
urls = ["https://tinyurl.com/hume-img"]
config = FaceConfig(identify_faces=True)
job = client.submit_job(urls, [config])

print(job)
print("Running...")

result = job.await_complete()
result.download_predictions("predictions.json")

print("Predictions downloaded!")

Rehydrate a batch job from a job ID

from hume import HumeBatchClient

client = HumeBatchClient("<your-api-key>")

job_id = "<your-job-id>"
job = client.get_job(job_id)

print(job)

Stream predictions over a websocket

Note: pip install hume[stream] is required to use websocket features

import asyncio

from hume import HumeStreamClient
from hume.models.config import FaceConfig

async def main():
    client = HumeStreamClient("<your-api-key>")
    config = FaceConfig(identify_faces=True)
    async with client.connect([config]) as socket:
        result = await socket.send_file("<your-image-filepath>")
        print(result)

asyncio.run(main())

Other Resources

Support

The Python SDK is open source! More details can be found on GitHub.

If you've found a bug with this SDK please open an issue!