Microsoft Copilot for Windows vs Sesame

Comparing the features of Microsoft Copilot for Windows to Sesame

Feature
Microsoft Copilot for Windows
Sesame

Capability Features

Automatic Conversation End
Chime Notification
Consistent Personality
Context Awareness
Conversational Dynamics
Conversational Speech Generation
Copilot Voice Floating UI
Copilot Wake Word
Dataset Size
1 million hours
Emotional Intelligence
Evaluation Suite
Feedback Mechanism
Hands-Free Voice Activation
Manual Conversation End
Mic Usage Indicator
Model Sizes
Tiny: 1B backbone, 100M decoderSmall: 3B backbone, 250M decoderMedium: 8B backbone, 300M decoder
Multiple Speaker Handling
Objective Metrics
Word Error RateSpeaker SimilarityHomograph DisambiguationPronunciation Consistency
On-Device Wake Word Detection
Partial Multilingual Support Planned
Planned for 20+ languages
Pronunciation Correction
Sequence Length
2048
Single-Stage Model
Subjective Metrics
Comparative Mean Opinion Score
Text and Audio Input
TextAudio
Training Epochs
5

Integration Features

GitHub Release
LLama Architecture Backbone
Microsoft Store Update
Mimi Split-RVQ Tokenizer

Limitation Features

Cannot Model Conversation Structure
English Language Dominance
Feature Not Default
Internet Required for Voice Responses
Memory Bottleneck in Training
No Local Audio Storage
No Pre-trained Language Model Use
Real-Time Generation Delay
RVQ time-to-first-audio scales poorly
Requires PC Unlocked
Version Requirement
1.25051.10.0 or higher
Wake Word Only in English
English only
Windows Insider Availability
Insiders only

Pricing Features

Free Preview
Open Source
Apache 2.0