Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Grok Voice 3.0 is an advanced speech-to-speech model that is accessible via the Grok Voice Agent API, designed for developers creating real-time voice applications. This model processes both audio and text inputs, delivering spoken audio or text outputs through a WebSocket connection while enabling features such as conversational turn-taking, interruptions, and function execution. Developers have the flexibility to link this model with custom functions and various server-side tools, which may include web searches, X searches, collections, or remote MCP servers. The API is crafted for use in interactive voice agents that enhance customer support and service call experiences, and it is also implemented for voice communication within Tesla vehicles and Grok Bot. Billing operates on a usage-based model, charging for audio by the minute and text input events separately. Additionally, the API documentation provides comprehensive setup instructions along with examples for clients using Python and JavaScript, ensuring that developers can easily integrate the functionality into their applications. This robust feature set empowers developers to create more engaging and efficient voice interaction systems.
Description
Voxtral Mini Transcribe 3, developed by Mistral AI, is an advanced speech-to-text model that transforms audio recordings into written transcripts via an API. Developers have the ability to submit audio files for bulk transcription, receiving text that includes timestamps and identifies different speakers. It provides support for transcription in multiple languages, incorporates speaker diarization, and allows for context biasing, enabling applications to introduce specific names or specialized terminology to enhance recognition accuracy. This model is specifically tailored for developers who are creating applications and audio workflows that require making recorded speech easily searchable, attributing dialogue to specific speakers, or synchronizing transcript segments with their corresponding audio. Teams can access the model through Mistral's hosted API, seamlessly integrating the resulting output into their software solutions, including transcription workflows and voice-responsive services. Unlike typical recording or editing applications, this offering is focused solely on the model and API functionalities. Furthermore, its capabilities make it a valuable asset for various industries aiming to streamline their audio data management processes.
API Access
Has API
Yes
API Access
Has API
Yes
Screenshots View All
No images available
Integrations
Grok
Yes
Grok Bot
Yes
Grok Voice Agent
Yes
Grok Voice Agent Builder
Yes
Model Context Protocol (MCP)
Yes
Twilio
Yes
Integrations
Grok
No
Grok Bot
No
Grok Voice Agent
No
Grok Voice Agent Builder
No
Model Context Protocol (MCP)
No
Twilio
No
Pricing Details
$0.08/min
Audio is $0.08 per minute. Text-only input events are $0.004 each. Server-VAD sessions are billed for the full session duration; push-to-talk sessions are billed for audio sent and received.
Free Trial
Yes
Free Version
No
Pricing Details
$0.0035/min
Standard input is $0.0035 per audio minute; cached input is $0.00035 per minute.
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
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
SpaceXSI
Founded
2023
Country
United States
Website
x.ai/api/voice
Vendor Details
Company Name
Mistral AI
Founded
2023
Country
France
Website
docs.mistral.ai/models/voxtral-mini-transcribe-3-0