iSpeech TTS & Speech API vs Sesame

Comparing the features of iSpeech TTS & Speech API to Sesame

Feature
iSpeech TTS & Speech API
Sesame

Capability Features

API Requests per Month
100000000
Cloud and Embedded TTS
Consistent Personality
Context Awareness
Conversational Dynamics
Conversational Speech Generation
Create IVR Prompts
Custom Voice Cloning
Dataset Size
1 million hours
Developer Signups
80000
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
Open Source SDKs
Partial Multilingual Support Planned
Planned for 20+ languages
Pronunciation Correction
SDK Availability
Sequence Length
2048
Single-Stage Model
Speech Rate Adjustment
SlowRegularFast
Speech Recognition
Subjective Metrics
Comparative Mean Opinion Score
Supported Language List
US EnglishUK EnglishAustralian EnglishUS SpanishChineseHong Kong ChineseTaiwan ChineseJapaneseKoreanCanadian EnglishHungarianBrazilian PortugueseEuropean PortugueseEuropean SpanishEuropean CzechEuropean DanishEuropean FinnishEuropean FrenchEuropean NorwegianEuropean DutchEuropean PolishEuropean ItalianEuropean TurkishEuropean GreekEuropean GermanRussianSwedishCanadian FrenchArabic
Talking Stickers
Text and Audio Input
TextAudio
Text to Speech
Training Epochs
5

Integration Features

Audiobook Support
Chrome Extension
Connected Vehicle Integration
GitHub Release
LLama Architecture Backbone
Mimi Split-RVQ Tokenizer
Mobile Integration
SAPI Integration

Limitation Features

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
Registration Required for Downloads
TTS for Non-Commercial Use Only

Pricing Features

Free Preview
Free Tier
IVR Prompts Free Sample
Open Source
Apache 2.0