Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
ElevenLabs has unveiled Scribe, a cutting-edge Automatic Speech Recognition (ASR) model that aims to provide remarkably accurate transcriptions in 99 different languages. This innovative system is tailored to effectively manage a wide range of real-world audio situations, featuring capabilities such as word-level timestamps, speaker identification, and audio-event tagging. In benchmark evaluations like FLEURS and Common Voice, Scribe has outperformed leading models, including Gemini 2.0 Flash, Whisper Large V3, and Deepgram Nova-3, achieving impressive word error rates of 98.7% for Italian and 96.7% for English. Additionally, Scribe shows a significant reduction in errors for languages that have often faced challenges, such as Serbian, Cantonese, and Malayalam, where competing models frequently report error rates above 40%. Furthermore, developers can easily incorporate Scribe into their applications via ElevenLabs' speech-to-text API, which returns structured JSON transcripts enriched with comprehensive annotations. This level of accessibility and performance is set to revolutionize the field of transcription and enhance the user experience across various applications.
Description
Voxtral Small Transcribe 3 is a versatile multilingual speech-to-text model tailored for converting recorded audio into text. Offered via an audio transcription API by Mistral, it incorporates features like timestamp documentation, speaker diarization, and context biasing, enabling developers to input key phrases that enhance the recognition of specific terms and names relevant to particular domains. This model is capable of automatically identifying supported languages or can utilize a specified language code, accommodating over 50 languages in total. It is particularly suitable for application developers focused on creating workflows for transcribing recorded audio, such as meetings, interviews, call transcriptions, customer service systems, and voice-agent processes. Additionally, Mistral outlines options for self-deployment of the Voxtral 3 series, which includes hosting on private clouds or on-premises solutions, making it adaptable to various organizational needs. Furthermore, the flexibility of the model ensures that it remains a valuable tool for enhancing communication efficiency across different sectors.
API Access
Has API
Yes
API Access
Has API
Yes
Integrations
ElevenLabs
Yes
JSON
Yes
MacWhisper
Yes
Mistral AI
No
SnapVee Studio
Yes
Integrations
ElevenLabs
No
JSON
No
MacWhisper
No
Mistral AI
Yes
SnapVee Studio
No
Pricing Details
$5 per month
Free Trial
No
Free Version
Yes
Pricing Details
$0.004/min
API usage is $0.004 per minute of audio.
Free Trial
No
Free Version
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
Yes
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
Yes
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
ElevenLabs
Founded
2022
Country
United Kingdom
Website
elevenlabs.io/blog/meet-scribe
Vendor Details
Company Name
Mistral AI
Founded
2023
Country
France
Website
docs.mistral.ai/models/voxtral-small-transcribe-3-0