Ausum vs Sesame

Comparing the features of Ausum to Sesame

Feature
Ausum
Sesame

Capability Features

Audio Summaries
Consistent Personality
Context Awareness
Conversational Dynamics
Conversational Speech Generation
Dataset Size
1 million hours
Emotional Intelligence
Evaluation Suite
Listen on-the-go
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
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
iPhone Support
LLama Architecture Backbone
Mimi Split-RVQ Tokenizer

Limitation Features

Android Support
Cannot Model Conversation Structure
English Language Dominance
Memory Bottleneck in Training
No Pre-trained Language Model Use
Private Beta
Real-Time Generation Delay
RVQ time-to-first-audio scales poorly
Requires Email Signup
Waitlist Access

Pricing Features

Free Preview
Free Stories
Open Source
Apache 2.0