Sesame vs Instant Singer

Comparing the features of Sesame to Instant Singer

Feature
Sesame
Instant Singer

Capability Features

Affiliate Program
Browser Based
Consistent Personality
Context Awareness
Conversational Dynamics
Conversational Speech Generation
Convert Any Song
Dataset Size
1 million hours
Discord Support
Emotional Intelligence
Evaluation Suite
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
Recording Song for Clone
Twinkle, Twinkle, Little Star
Sample Selection
Guy 1👨👩
Sequence Length
2048
Single-Stage Model
Subjective Metrics
Comparative Mean Opinion Score
Text and Audio Input
TextAudio
Training Epochs
5
Voice Cloning
Voice Swap
YouTube Link Conversion

Integration Features

GitHub Release
LLama Architecture Backbone
Mimi Split-RVQ Tokenizer

Limitation Features

Cannot Model Conversation Structure
English Language Dominance
Max Free Clones
1
Max Free Samples
4
Memory Bottleneck in Training
No API Mentioned
No Credit Card Required
No Mention of Download Formats
No Pre-trained Language Model Use
Real-Time Generation Delay
RVQ time-to-first-audio scales poorly

Pricing Features

Credit-Based Pricing
Free Converted Samples
4
Free Preview
Free Tier
Free Voice Clone Limit
1
Lite Pack Minimum Credits
2
Lite Pack Price Per Credit
$1.99/credit
Open Source
Apache 2.0
Pro Pack Minimum Credits
8
Pro Pack Price Per Credit
$1.49/credit