Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
Groq Inc. has launched support for OpenAI's Whisper-large-v3 model, offering ultra-fast transcription services. The model, which transcribes speech to text at a speed of 140 times faster than traditional methods, supports multiple file formats and languages. It is available for free to regular users and costs $0.03 per hour of transcription for others. The Whisper API can handle up to 25 MB files and integrates easily with other tools such as GPT-4o for downsampling audio files. GroqNotes, a tool that turns audio into organized notes, has also been introduced and is available on Replit. Additionally, the model processes at 1200+ tokens/second and benchmark results are expected soon.
GroqNotes is now on @Replit! Experience the speed of Whisper on @GroqInc transcribing audio and converting to structured notes. Also new ✨: Choose between using different models on Groq under experimental customizations settings. Links in reply below: https://t.co/iMogQ8bS3c https://t.co/UyedPS25zd
Groq has launched the whisper-large-v3 model, featuring 140x speed for ultra-fast transcription, supporting multiple file formats, and it's free for regular users! 📌 Multi-language support: Transcribe and translate! 📌 Convenient API: Easy integration, no complex applications… https://t.co/1a31ojsg1l
. @GroqInc Whisper support has landed in Indexify. Currently running transcription benchmarks between Groq, open-source whisper on NVIDIA 3090, and Apple’s whisper-mlx. Code and benchmark results soon.
