Home
Articles
Salaries
Sign in
Home
OpenAI Whisper Transcription
Compared to Sesame
OpenAI Whisper Transcription vs Sesame
Comparing the features of OpenAI Whisper Transcription to Sesame
Feature
OpenAI Whisper Transcription
Sesame
Capability Features
Audio Transcription
Audio Upload
Browser-Based Partitioning
Consistent Personality
Context Awareness
Conversational Dynamics
Conversational Speech Generation
Dataset Size
1 million hours
Demo Mode
Emotional Intelligence
Evaluation Suite
Model Sizes
Tiny: 1B backbone, 100M decoder
Small: 3B backbone, 250M decoder
Medium: 8B backbone, 300M decoder
Multiple Speaker Handling
Objective Metrics
Word Error Rate
Speaker Similarity
Homograph Disambiguation
Pronunciation Consistency
One-Click Transcription
Partial Multilingual Support Planned
Planned for 20+ languages
Pronunciation Correction
Sequence Length
2048
Single-Stage Model
Subjective Metrics
Comparative Mean Opinion Score
Text and Audio Input
Text
Audio
Training Epochs
5
Integration Features
GitHub Release
LLama Architecture Backbone
Mimi Split-RVQ Tokenizer
OpenAI Whisper Integration
Supported Audio Types
mp3
mp4
mpeg
mpga
m4a
wav
webm
Limitation Features
Cannot Model Conversation Structure
English Language Dominance
Memory Bottleneck in Training
No Built-in Whisper
No Mention of Price Plans
No Pre-trained Language Model Use
Real-Time Generation Delay
RVQ time-to-first-audio scales poorly
Requires OpenAI API Key
Pricing Features
Free Preview
Free Trial/Demo
Open Source
Apache 2.0