Bocca vs Sesame

Comparing the features of Bocca to Sesame

Feature
Bocca
Sesame

Capability Features

AI Models Used
Audio Transcription
Consistent Personality
Context Awareness
Conversational Dynamics
Conversational Speech Generation
Dataset Size
1 million hours
Emotional Intelligence
Evaluation Suite
Model Sizes
Tiny: 1B backbone, 100M decoderSmall: 3B backbone, 250M decoderMedium: 8B backbone, 300M decoder
Multi-language Support
Multiple Speaker Handling
Objective Metrics
Word Error RateSpeaker SimilarityHomograph DisambiguationPronunciation Consistency
Offline Mode
Partial Multilingual Support Planned
Planned for 20+ languages
Priority Support
Private Local Processing
Pronunciation Correction
Push-to-Talk Mode
Sequence Length
2048
Single-Stage Model
Subjective Metrics
Comparative Mean Opinion Score
Text and Audio Input
TextAudio
Training Epochs
5

Integration Features

App Integration
Works with any app
GitHub Release
LLama Architecture Backbone
Mac Compatibility
Mimi Split-RVQ Tokenizer

Limitation Features

Cannot Model Conversation Structure
English Language Dominance
Intel Mac Support
Unclear
Internet Required
Memory Bottleneck in Training
No Pre-trained Language Model Use
Real-Time Generation Delay
RVQ time-to-first-audio scales poorly
Windows Compatibility

Pricing Features

Free Preview
Free Tier
Open Source
Apache 2.0
Premium Plan
One-time $25
Subscription Required
Transcription Free Limit
50
Transcription Limit Premium
Unlimited
Trial Available