SonicCloud vs Sesame

Comparing the features of SonicCloud to Sesame

Feature
SonicCloud
Sesame

Capability Features

Address Hearing Challenges
Difficulty following conversationsFatigue in calls or video meetingsDifficulty hearing music and videos
Audiologist-Developed Solution
Consistent Personality
Context Awareness
Conversational Dynamics
Conversational Speech Generation
Dataset Size
1 million hours
Digital Solution
Emotional Intelligence
Enhances Streaming
Enhances Video Calls
Evaluation Suite
Hearing Test Feature
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
Personalized Hearing Adjustment
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
Mimi Split-RVQ Tokenizer

Limitation Features

Cannot Model Conversation Structure
English Language Dominance
Memory Bottleneck in Training
No Integration Details
No Mention of File Format Support
No Pre-trained Language Model Use
No Pricing Plans Listed
Real-Time Generation Delay
RVQ time-to-first-audio scales poorly

Other Features

Recognition: Amazon Alexa Voice First Winner
Recognition: Apple Editorial Board App of the Day
Recognition: World Changing Idea Finalist
Trusted by Audiologists
Used in Organizations

Pricing Features

Free Preview
Free Trial
30-days
Open Source
Apache 2.0