Combine on-device wake word detection with speaker recognition so a phrase like "Alexa" wakes the device only when the enrolled user says it. No cloud. No audio uploaded. Works offline.
Personalized wake words, combining always-on wake word detection with speaker verification, only trigger when the enrolled user says them — so identical phrases from different speakers are treated differently. Most speaker recognition engines require 2–3 seconds of continuous speech for reliable identification, with accuracy degrading significantly below one second. That's why only a few companies, such as Alexa Voice ID by Amazon and Personalized Hey Siri by Apple, can offer personalized wake words in production. This guide shows how Picovoice's Porcupine Wake Word and Eagle Speaker Recognition compose into a self-contained personalized wake word that can be deployed at scale.
Equal Error Rate (EER) is the operating point where the false-accept rate equals the false-reject rate, showing the ability of popular speaker recognition alternatives; the lower the better. Across four wake words, Eagle achieves two perfect 0.00% EER scores on wake words Jarvis and Snowboy, where Pyannote and SpeechBrain land at 0.71% & 0.75% and 0.36% & 0.35% respectively. On Alexa, Eagle's 0.15% EER is roughly 7× lower than both competitors at 1.08%. On Smart Mirror, all three engines reach 0.38%. Across all four wake words, Eagle's mean EER (0.13%) is about 5× lower than Pyannote (0.63%) or SpeechBrain (0.64%).
For a personalized wake word that needs to reject impostors reliably, Eagle offers production-grade accuracy at wake word length audio, allowing enterprises to build experiences similar to Google Voice Match, Apple's Personalized Hey Siri, and Amazon's VoiceID, with no dependency on Google, Apple, or Amazon.
| alexa | jarvis | smart mirror | snowboy | average | |
|---|---|---|---|---|---|
| EagleThis recipe | 0.15 | 0.00Perfect | 0.38 | 0.00Perfect | 0.13 |
| Pyannote | 1.08 | 0.71 | 0.38 | 0.36 | 0.63 |
| SpeechBrain | 1.08 | 0.75 | 0.38 | 0.35 | 0.64 |
Porcupine Wake Word is lightweight, accurate, customizable, and production-ready. With Porcupine, enterprises can train branded wake words and always-listening commands in seconds and deploy them across platforms. Industry-leading accuracy fits in even MCUs.
Eagle Speaker Recognition achieves a mean equal error rate of 0.13% across four wake words, roughly 5× lower than Pyannote (0.63%) and SpeechBrain (0.64%). On Alexa, Eagle's 0.15% EER is roughly 7× lower than both competitors at 1.08%. Eagle performs reliable speaker verification (1:1) and identification (1:N) on short audios, such as wake words, with no audio sent to a cloud.
Smart speakers, displays, and home hubs serving multiple family members can route the wake word to the right user profile — kid asks for music, the hub plays from their playlist; parent asks for the calendar, the hub answers from theirs.
Earbuds and watches have single-digit memory budgets and zero room for cloud. Porcupine and Eagle fit in embedded devices. So only the wearer's wake word triggers, even when they share a kitchen with three other voices.
Cars need wake words that ignore the passengers. Combine Porcupine with Eagle speaker verification so only the driver's wake phrase triggers driving-relevant actions and brings driver settings, while passengers summon entertainment with a different or no profile.
Hands-free industrial HMIs, surgical ORs, medical bedside devices, and field tools need a wake word that won't fire on coworkers but only authorized personnel. Personalized and secure wake word gates the device to the operator on shift.
A complete working recipe in Python. Open-source on GitHub. Runs 100% on-device.