Home
Articles
Home
Sesame
Compared to WhisperBot
Sesame vs WhisperBot
Comparing the features of Sesame to WhisperBot
Feature
Sesame
WhisperBot
Capability Features
Consistent Personality
Content Auto-Deletion
30 minutes
Context Awareness
Conversational Dynamics
Conversational Speech Generation
Database Erasure Policy
Dataset Size
1 million hours
Emotional Intelligence
End-to-End Encryption
Evaluation Suite
High Accuracy Model
95%
Instant Transcription
Key Takeaways Feature
Model Sizes
Tiny: 1B backbone, 100M decoder
Small: 3B backbone, 250M decoder
Medium: 8B backbone, 300M decoder
Multi-language Support
57
Multiple Speaker Handling
No Extra App Required
Objective Metrics
Word Error Rate
Speaker Similarity
Homograph Disambiguation
Pronunciation Consistency
Partial Multilingual Support Planned
Planned for 20+ languages
Powered by OpenAI
Pronunciation Correction
Sequence Length
2048
Single-Stage Model
Speech to Text
Subjective Metrics
Comparative Mean Opinion Score
Text and Audio Input
Text
Audio
Training Epochs
5
Integration Features
GitHub Release
LLama Architecture Backbone
Mimi Split-RVQ Tokenizer
WhatsApp Integration
Limitation Features
Cannot Model Conversation Structure
English Language Dominance
Memory Bottleneck in Training
No API or Plugin Integration
No Export Features
No Manual Data Retention
No Pre-trained Language Model Use
Real-Time Generation Delay
RVQ time-to-first-audio scales poorly
WhatsApp Only
Pricing Features
Free Preview
Has Free Tier
One-Time Payment
Open Source
Apache 2.0