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
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.
API Access
Has API
API Access
Has API
Integrations
Alibaba Cloud Model Studio
ElevenLabs
JSON
MacWhisper
SnapVee Studio
Integrations
Alibaba Cloud Model Studio
ElevenLabs
JSON
MacWhisper
SnapVee Studio
Pricing Details
No price information available.
Free Trial
Free Version
Pricing Details
$5 per month
Free Trial
Free Version
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Vendor Details
Company Name
Alibaba
Founded
1999
Country
China
Website
alibabacloud.com
Vendor Details
Company Name
ElevenLabs
Founded
2022
Country
United Kingdom
Website
elevenlabs.io/blog/meet-scribe