Sesame vs Narakeet

Comparing the features of Sesame to Narakeet

Feature
Sesame
Narakeet

Capability Features

Auto Subtitle Generator
Bulk Video Creation
Consistent Personality
Context Awareness
Conversational Dynamics
Conversational Speech Generation
Dataset Size
1 million hours
Document to Audio
WordPDFEPUB
Documentation Video Automation
Emotional Intelligence
Evaluation Suite
Full HD Video Output
Images and Audio to Video
Industry Use Cases
AnnouncementsPodcastsLanguage LessonsAudiobooksVideo LectureProperty RentalCorporate TrainingScreencasts
Model Sizes
Tiny: 1B backbone, 100M decoderSmall: 3B backbone, 250M decoderMedium: 8B backbone, 300M decoder
Multi-Language Support
Multiple Speaker Handling
Objective Metrics
Word Error RateSpeaker SimilarityHomograph DisambiguationPronunciation Consistency
Partial Multilingual Support Planned
Planned for 20+ languages
PPT to Video
Pronunciation Correction
Resolution Variants
Scripted Stage Directions
Sequence Length
2048
Single-Stage Model
Slides to Video
Social Media Templates
InstagramLinkedInFacebookTwitter
Subjective Metrics
Comparative Mean Opinion Score
Subtitle File Generation
Subtitles to Audio
SRTWebVTT
Supported Language List
100
Text and Audio Input
TextAudio
Text to Speech
Training Epochs
5
Video Editing via Text
Voiceover Synchronization
Voices Available
800

Integration Features

API Access
Command Line Client
File Format Support
WordPDFEPUBPowerPointMarkdownSRTWebVTTImagesVideo Clips
GitHub Release
Google Slides Integration
Keynote Integration
LLama Architecture Backbone
Markdown Scripting
Mimi Split-RVQ Tokenizer
Platform Compatibility
YouTubeInstagramLinkedInFacebookTwitter

Limitation Features

Browser Video Playback
Cannot Model Conversation Structure
English Language Dominance
Memory Bottleneck in Training
No Pre-trained Language Model Use
Real-Time Generation Delay
RVQ time-to-first-audio scales poorly
Voice Recording

Pricing Features

Free Preview
Free Tier
Open Source
Apache 2.0