Overview
About this model
Speaker diarization — detects who spoke when. Returns speaker turns with start/end times; pair with a transcription model for labelled transcripts.
View model card on HuggingFaceSpecifications
Model details
- Provider
- pyannote
- Modality
- Diarization
- Pricing
- $4.00 / 1M tok
API
Call it in code
One OpenAI-compatible API. Swap the model id and you're done.
import requests
BASE_URL = "https://api.ecohash.com/v1"
HEADERS = {"Authorization": "Bearer YOUR_API_KEY"}
turns = requests.post(
f"{BASE_URL}/audio/diarizations",
headers=HEADERS,
data={"model": "pyannote-diarization-3-1"},
files={"file": open("meeting.wav", "rb")},
).json() # speaker turns with start/end times