Celebrity Voice AI vs Sesame

Comparing the features of Celebrity Voice AI to Sesame

Feature
Celebrity Voice AI
Sesame

Capability Features

Celebrity Types
ActorsAthletesMusiciansCrypto PersonalitiesCartoon CharactersRoyalty
Celebrity Voices
100
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
Multiple Speaker Handling
New Voices Added Weekly
Number of Messages Generated
1000000
Number of Users
50000
Objective Metrics
Word Error RateSpeaker SimilarityHomograph DisambiguationPronunciation Consistency
Partial Multilingual Support Planned
Planned for 20+ languages
Pronunciation Correction
Quick Generation
Realistic AI Voices
Sequence Length
2048
Single-Stage Model
Subjective Metrics
Comparative Mean Opinion Score
Supported Message Types
Custom messages spoken by celebrity voices
Supported Personalities
Morgan FreemanSpongeBobBen PasternakImran KhanThread GuyAnatoly YakovenkoAnsemVirat KohliDavid GogginsJustine MoorePatrickQueen Elizabeth IIIce SpiceDrakeOrangieMurad
Text and Audio Input
TextAudio
Training Epochs
5
Unlimited Possibilities

Integration Features

API Access
Discord Integration
GitHub Release
LLama Architecture Backbone
Mimi Split-RVQ Tokenizer
Plugin Support

Limitation Features

Cannot Model Conversation Structure
English Language Dominance
Export or Download Feature
File Formats Supported
Unknown
Limits and Quotas
Not specified
Memory Bottleneck in Training
No Pre-trained Language Model Use
Real-Time Generation Delay
RVQ time-to-first-audio scales poorly
Supported Language List
Unknown (likely English only)

Pricing Features

Free Preview
Free Tier
Open Source
Apache 2.0
Trial Period