Metadata-Version: 2.4
Name: phonexia-speaker-identification-client
Version: 1.0.0
Summary: Client for communication with Phonexia speaker identification microservice.
Author-email: Phonexia <info@phonexia.com>
Keywords: grpc,voice,voice-biometry,speech,language,identification
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: more-itertools>=10.6.0
Requires-Dist: phonexia-grpc>=2.31.2
Requires-Dist: numpy>=2.0.0; python_version >= "3.12"
Requires-Dist: numpy<2.0.0; python_version < "3.12"
Requires-Dist: typer>=0.16.0
Requires-Dist: soundfile>=0.13.0

![](https://www.phonexia.com/wp-content/uploads/phonexia-logo-transparent-500px.png)

# Phonexia speaker identification client

This module contains client for communication with [speaker identification microservice](https://hub.docker.com/repository/docker/phonexia/speaker-identification/general) developed by [Phonexia](https://phonexia.com).

The client covers all functionality exposed by the microservice: extracting voiceprints from audio (`extract`), comparing them (`compare`), merging them (`merge`) and converting them to a vector database format (`convert`).

To use this client you will first need a running instance of any *Phonexia speaker identification microservice*. If you don't yet have any running instance, don't hesitate to [contact our sales department](mailto:info@phonexia.com).

You can learn more about the speaker identification technology [here](https://docs.phonexia.com/products/speech-platform-4/technologies/speaker-identification/).

On [this page](https://docs.phonexia.com/products/speech-platform-4/grpc/api/phonexia/grpc/technologies/speaker_identification/v1/speaker_identification.proto), you will find a *gRPC API* reference for *speaker identification microservice*.
