Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Qwen-Audio-3.0-TTS-Flash is a real-time version of Qwen-Audio-3.0-TTS, specifically optimized for interactive uses with a first-packet latency around 300 milliseconds. It boasts support for 16 different languages and enhanced fidelity for various Chinese dialects. In multilingual assessments, Flash achieves the lowest average word error rate and character error rate in its category at 3.87, demonstrating impressive clarity while maintaining the unique characteristics of different speakers across multiple languages. Developers can efficiently manage the output using straightforward language instructions, rather than fine-tuning acoustic settings manually, which allows them to influence aspects like emotion, role, scenario, pace, projection, and tone through intuitive prompts. Additionally, inline tags enable the integration of specific non-verbal cues, making this model ideal for an array of applications, including conversational agents, storytelling, gaming, dubbing, and other expressive speech scenarios. Voice cloning capabilities are also included, designed to perform well even with less-than-perfect reference audio; targeted acoustic simulation effectively reduces background noise and reverberation while ensuring the original voice's tonal qualities are preserved. Overall, this advanced technology allows for a more versatile and engaging audio experience across various platforms and applications.
Description
Voxtral Mini Transcribe Realtime 3 is an advanced speech-to-text solution offered via Mistral’s API, designed for applications requiring immediate transcription capabilities. It utilizes WebSocket technology to stream audio and delivers transcription events in real-time as individuals speak, with adjustable streaming latencies. This model is ideal for developers looking to incorporate live captions, enhance voice assistant functionalities, or streamline voice-agent processes with accurate transcription. Notably, it includes features such as turn detection, speaker diarization, and context biasing tailored for specialized vocabulary, and it accommodates transcription in 45 different languages and dialects. Users can connect seamlessly to the real-time endpoint, allowing them to receive transcription events as audio is processed, eliminating the need to wait for a complete audio recording to finish. As a member of Mistral’s Voxtral audio model family, Voxtral Mini Transcribe Realtime 3 stands out for its versatility and efficiency in a variety of applications. This capability makes it an essential tool for developers aiming to enhance user interaction through immediate and accurate voice transcription.
API Access
Has API
Yes
API Access
Has API
Yes
Integrations
Alibaba Cloud Model Studio
Yes
LiveKit
No
Mistral AI
No
QwenCloud
Yes
Integrations
Alibaba Cloud Model Studio
No
LiveKit
Yes
Mistral AI
Yes
QwenCloud
No
Pricing Details
No price information available.
Free Trial
Yes
Free Version
No
Pricing Details
$0.008/min
Usage-based pricing is $0.008 per minute of realtime transcription 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)
Yes
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
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
Alibaba
Founded
1999
Country
China
Website
alibabacloud.com
Vendor Details
Company Name
Mistral AI
Founded
2023
Country
France
Website
docs.mistral.ai/models/voxtral-mini-transcribe-realtime-3-0