Sesame vs Whisper API

Comparing the features of Sesame to Whisper API

Feature
Sesame
Whisper API

Capability Features

Consistent Personality
Context Awareness
Conversational Dynamics
Conversational Speech Generation
Dataset Size
1 million hours
Emotional Intelligence
Evaluation Suite
Language/Country Support
100+ languages
Latest Whisper Model
Whisper Large V3
Model Sizes
Tiny: 1B backbone, 100M decoderSmall: 3B backbone, 250M decoderMedium: 8B backbone, 300M decoder
Multiple Speaker Handling
Non-Developer Access
Objective Metrics
Word Error RateSpeaker SimilarityHomograph DisambiguationPronunciation Consistency
Partial Multilingual Support Planned
Planned for 20+ languages
Pronunciation Correction
Response Format Selection
json
Scale for Millions
Sequence Length
2048
Single-Stage Model
Speaker Diarization
Speaker Labels
Subjective Metrics
Comparative Mean Opinion Score
Summary Generation
Text and Audio Input
TextAudio
Training Epochs
5
Translation Capability

Integration Features

API Integrations
File Formats Supported
mp3videopodcastsmeetings
GitHub Release
LLama Architecture Backbone
Mimi Split-RVQ Tokenizer
OpenAI API Compatibility
Programming Language Agnostic

Limitation Features

Cannot Model Conversation Structure
English Language Dominance
Memory Bottleneck in Training
No OpenAI Affiliation
No Pre-trained Language Model Use
Real-Time Generation Delay
RVQ time-to-first-audio scales poorly

Pricing Features

Free Preview
Free Transcription Hours
30
Free Trial Package
Hourly Pricing
$0.17/hour
Open Source
Apache 2.0
Trial Period
1 month