MakePodcast vs Sesame

Comparing the features of MakePodcast to Sesame

Feature
MakePodcast
Sesame

Capability Features

Ad Read Generation
Browser-based Security
Consistent Personality
Content Repurposing
Context Awareness
Conversational Dynamics
Conversational Speech Generation
Custom Voice Creation
Dataset Size
1 million hours
ElevenLabs Supported Languages
EnglishHindiPortugueseChineseSpanishFrenchGermanJapaneseArabicRussianKoreanIndonesianItalianDutchTurkishPolishSwedishFilipinoMalayRomanianUkrainianGreekCzechDanishFinnishBulgarianCroatianSlovakTamil
Emotional Intelligence
Evaluation Suite
Fast Audio Generation
Model Sizes
Tiny: 1B backbone, 100M decoderSmall: 3B backbone, 250M decoderMedium: 8B backbone, 300M decoder
Multi-language Support
Multiple Hosts Support
Multiple Speaker Handling
No Host Limit
No Script Length Limit
Objective Metrics
Word Error RateSpeaker SimilarityHomograph DisambiguationPronunciation Consistency
OpenAI Supported Languages
AfrikaansArabicArmenianAzerbaijaniBelarusianBosnianBulgarianCatalanChineseCroatianCzechDanishDutchEnglishEstonianFinnishFrenchGalicianGermanGreekHebrewHindiHungarianIcelandicIndonesianItalianJapaneseKannadaKazakhKoreanLatvianLithuanianMacedonianMalayMarathiMaoriNepaliNorwegianPersianPolishPortugueseRomanianRussianSerbianSlovakSlovenianSpanishSwahiliSwedishTagalogTamilThaiTurkishUkrainianUrduVietnameseWelsh
Partial Multilingual Support Planned
Planned for 20+ languages
Podcast Generation
Pronunciation Correction
Script Import
Script Upload
Sequence Length
2048
Single-Stage Model
Social Media Voiceovers
TikTokReelsShortsother social platforms
Subjective Metrics
Comparative Mean Opinion Score
Text and Audio Input
TextAudio
Training Epochs
5
Voice Options
20

Integration Features

API Key Authentication
GitHub Release
LLama Architecture Backbone
Mimi Split-RVQ Tokenizer
Supported TTS Providers
OpenAIElevenLabs

Limitation Features

Cannot Model Conversation Structure
Commercial Use Disclosure
Disclosure required for OpenAI commercial TTS
Commercial Use with ElevenLabs
Paid plan required for commercial use
English Language Dominance
Free Plan Limits
Requires OpenAI/ElevenLabs API keys and credits
Memory Bottleneck in Training
No Pre-trained Language Model Use
Real-Time Generation Delay
RVQ time-to-first-audio scales poorly
Refund Policy
No refunds after purchase
Requires External API Credits

Pricing Features

Free Preview
Free Tier
Lifetime Plan
Lifetime Plan Price
$49 USD
Open Source
Apache 2.0
Unlimited Episodes