Eagle Speaker Recognition Engine
C Quick Start
- Linux (x86_64)
- macOS (x86_64, arm64)
- Windows (x86_64)
- NVIDIA Jetson Nano
- Raspberry Pi (3, 4)
Picovoice Account & AccessKey
Signup or Login to Picovoice Console to get your
Make sure to keep your
Eagle consists of two distinct steps: Enrollment and Recognition. In the enrollment step, Eagle analyzes a series of
utterances from a particular speaker to learn their unique voiceprint. This step results in a
which can be stored and utilized during inference. During the Recognition step, Eagle compares the incoming frames of
audio to the voiceprints of all enrolled speakers in real-time to determine the similarity between them.
- Clone the repository:
- Include the public header files (
- Link the project to an appropriate precompiled library for the target platform and load it.
- Construct an instance of the profiler:
- Pass in audio to the
pv_eagle_profiler_enrollfunction to enroll a speaker:
- Release resources explicitly when done with the profiler:
- Construct an instance of the engine:
- Pass audio frames to the
pv_eagle_processfunction to perform speaker recognition:
- Release resources explicitly when done with the engine:
For the Eagle SDK, we offer demo applications that demonstrate how to use the speaker recognition engine on real-time audio streams (i.e. microphone input) and audio files.
- Clone the Eagle repository from GitHub using HTTPS:
- Build the microphone demo:
To see the usage options for the demo:
Ensure you have a working microphone connected to your system and run the command corresponding to your platform to either enroll a speaker or perform speaker recognition:
For more information on our Eagle demos for C, head over to our GitHub repository .