Eagle Speaker Recognition

Verify and identify speakers during natural conversations

Cross-platform, text-independent, language-agnostic speaker recognition with a seamless enrollment process, readily available to all developers

Click on "Enroll a speaker"
to get started
Trusted by thousands of enterprises - from startups to Fortune 500s
Loved by 200,000+ developers

What is Eagle Speaker Recognition?

Eagle Speaker Recognition is speaker verification and identification software that distinguishes individuals using their unique voice characteristics.

Eagle Speaker Recognition, powered by deep learning, enables developers to determine “who is speaking” on any platform with no language or passphrase limitations.

Cross-platform Speaker Recognition with native SDKs in minutes

# Speaker Enrollment
o = pveagle.create_profiler(access_key)
while percentage < 100:
percentage, feedback = o.enroll(
speaker_profile = o.export()
# Speaker Recognition
eagle = pveagle.create_recognizer(
while True:
scores = eagle.process(

Why Eagle Speaker Recognition?

Eagle Speaker Recognition is the only readily available production-grade, highly accurate, resource-efficient, cross-platform, text-independent, and language-agnostic engine with a seamless enrollment process.

Deploy in Minutes, Enroll in Seconds

Get to know users, personalize experiences, and build trust.

  • 🤸
  • ⏱️
    Optimized for real-time
  • 🌎
  • 🔤
  • 💪
    Free Plan
  • 🚀
    Ready to deploy
  • 🤗
    Easy enrollment in seconds
  • 🧠
    Powered by deep learning
Easy enrollment in seconds

Frictionless user experiences

Make the enrollment process seamless and natural instead of forcing a long, separate process or specific passphrases. It takes just a few seconds, try now!
Click on "Enroll a speaker"
to get started
Powered by Deep Learning

Best-in-class Performance

Compare Detection Accuracy and Detection Error Rate of Speaker Recognition engines using open-source benchmarks. Eagle outperforms SpeechBrain, pyannote, and WeSpeaker at detecting speakers.
2024-03-21T11:25:00.617105image/svg+xmlMatplotlib v3.7.1, https://matplotlib.org/

Less is more

Eagle Speaker Recognition achieves higher detection accuracy using hundreds of times less compute and memory, returning fast results across platforms.
2024-03-21T11:25:00.901691image/svg+xmlMatplotlib v3.7.1, https://matplotlib.org/
Text-Independent, Language-Agnostic

Grow globally, scale with no limits

Recognize speakers instantly with high accuracy across the world with language-agnostic and text-independent Eagle Speaker Recognition.

Unify Speaker Identification and Verification

Offer the same experience across all channels, including the web and mobile. Embed speaker recognition into your product without worrying about future expansions.
Get started with

Eagle Speaker Recognition

Start verifying and identifying users with Eagle Speaker Recognition in less than 10 minutes.

Start Now
Forever Free Plan
  • Production-ready
  • Cross-platform SDKs
  • Text-independent
  • Language-independent
Learn more about

Eagle Speaker Recognition

What is speaker recognition?

Speaker Recognition deals with speaker identification and verification using distinguishable voice characteristics. It focuses on “who” rather than “what”.

What’s speaker identification?

Speaker Identification, also known as Speaker Search or Speaker Spotting, is a special application of speaker recognition that determines the identity of an unknown speaker by comparing their characteristics with the voice characteristics of known speakers.

What’s speaker verification?

Speaker Verification, also known as Voice Biometrics, Voice Authentication, and Voiceprinting is a subset of speaker recognition that focuses on verifying individuals’ identities using unique voice patterns.

What’s the difference between speaker verification and speaker identification?

Speaker Identification and Speaker Verification are both subsets of Speaker Recognition. If a Speaker Recognition engine does a one-to-one match to verify the claimed identity, it’s called Speaker Verification. If it does a one-to-many match, i.e., determines the speaker’s identity within a group of enrolled speakers, it’s called Speaker Identification.

How can I select the best speaker recognition engine?

The best speaker recognition engine varies among enterprises, depending on their priorities and needs. Performance, Platform Support, Scalability, Compliance, Ease of Use, Developer-Friendliness, Availability of Support, and the Total Cost of Ownership are the most important factors to consider before a decision.

How can I validate the accuracy of Eagle Speaker Recognition?

Picovoice researchers published an open-source speaker recognition benchmark to give developers a head-start with evals. You can reproduce it or use your test data. If you’re not familiar with the most used metrics in speaker recognition performance evals, check out the speaker recognition performance measurement and comparison guide.

Which platforms does Eagle Speaker Recognition support?

How do I get technical support for Eagle Speaker Recognition?

Picovoice docs, blog, Medium posts, and GitHub are great resources to learn about voice AI, Picovoice technology, and how to detect who is speaking. You can report bugs and issues on GitHub. If you need help with developing your product, you can purchase the optional Support Add-on or upgrade your account to the Developer Plan.

How can I get informed about updates and upgrades?

Version changes appear in the and LinkedIn. Subscribing to GitHub is the best way to get notified of patch releases. If you enjoy building with Eagle Speaker Recognition, show it by giving a GitHub star!