Silvia vs Sesame

Comparing the features of Silvia to Sesame

Feature
Silvia
Sesame

Capability Features

Adaptive Dictation
Consistent Personality
Context Awareness
Conversational Dynamics
Conversational Speech Generation
Dataset Size
1 million hours
Dictation Extension
Emotional Intelligence
Evaluation Suite
Finish Speaking Detection
Model Sizes
Tiny: 1B backbone, 100M decoderSmall: 3B backbone, 250M decoderMedium: 8B backbone, 300M decoder
Multilingual Input
Multiple Speaker Handling
Objective Metrics
Word Error RateSpeaker SimilarityHomograph DisambiguationPronunciation Consistency
Partial Multilingual Support Planned
Planned for 20+ languages
Pronunciation Correction
Seamless Language Switching
Sequence Length
2048
Single-Stage Model
Subjective Metrics
Comparative Mean Opinion Score
Supports English and Spanish
EnglishSpanish
Text and Audio Input
TextAudio
Training Epochs
5
Upcoming Language Support
FrenchRomanianGermanDutch

Integration Features

App Store Availability
Chat Platform Integration
iMessageWhatsAppSignalTelegramMessengerany other app where you type
GitHub Release
LLama Architecture Backbone
Mimi Split-RVQ Tokenizer

Limitation Features

Cannot Model Conversation Structure
English Language Dominance
Memory Bottleneck in Training
No Android Support
No Mention of Export Options
No Pre-trained Language Model Use
No Web Platform
Real-Time Generation Delay
RVQ time-to-first-audio scales poorly

Pricing Features

Free Preview
Free Tier
Open Source
Apache 2.0