Sesame vs Speechly

Comparing the features of Sesame to Speechly

Feature
Sesame
Speechly

Capability Features

Automatic Formatting
Consistent Personality
Context Awareness
Conversational Dynamics
Conversational Speech Generation
Custom Vocabulary Support
Custom Voice Commands
Dataset Size
1 million hours
Email Mode
Emotional Intelligence
Enterprise Grade Security
Evaluation Suite
Fast Transcription Speed
Under 3 seconds
Long-Form Resilience
Message Mode
Model Sizes
Tiny: 1B backbone, 100M decoderSmall: 3B backbone, 250M decoderMedium: 8B backbone, 300M decoder
Multilingual Support
150+ languages
Multiple Speaker Handling
No Missed Context
Objective Metrics
Word Error RateSpeaker SimilarityHomograph DisambiguationPronunciation Consistency
Partial Multilingual Support Planned
Planned for 20+ languages
Prompt Mode
Pronunciation Correction
Sequence Length
2048
Single-Stage Model
Subjective Metrics
Comparative Mean Opinion Score
Text and Audio Input
TextAudio
To-Do Mode
Training Epochs
5
Transcription Speed
180+ words per minute
Voice-to-Text
Works Across Apps

Integration Features

GitHub Release
LLama Architecture Backbone
Mimi Split-RVQ Tokenizer
Platform Integrations
GmailSlackNotionDiscord
Supported Platforms
MacOS

Limitation Features

API or Plugin Integration
Cannot Model Conversation Structure
English Language Dominance
File Formats Supported
Not specified
Memory Bottleneck in Training
Minimum OS Requirements
MacOS Ventura 13.1 or higher
No Pre-trained Language Model Use
Platform Limitation
MacOS only
Real-Time Generation Delay
RVQ time-to-first-audio scales poorly
User Limit
Not specified

Pricing Features

Free Preview
Free Tier
No Credit Card Required
Open Source
Apache 2.0