Grok launches Voice Transcribe 2.0

Grok has announced the launch of its new model, Voice Transcribe 2.0.

Grok is launching a new speech-to-text model.

The well-known language model, developed by xAI, has announced the launch of Grok Voice Transcribe 2.0, and the updated technology has been billed as “one of the most accurate transcription models available today”.

The company said in a statement: “We’re releasing Grok Voice Transcribe 2.0, our latest speech-to-text model. Across our real-world evaluations, Grok Voice Transcribe 2.0 is one of the most accurate transcription models available today and twice as accurate as Grok Voice Transcribe 1.0, at the same price.

“Grok Voice Transcribe 2.0 is built on the audio foundation model behind Grok Voice. Grok Voice already powers tens of thousands of customer-support calls a day, transcribes millions of hours of video narration, and runs voice agents in physical products, including the Grok assistant in Tesla vehicles. It is trained on a unique dataset of live, noisy, multilingual audio recorded across a diverse set of environments and refined with post-training.

“The result is one of the most accurate transcription models for speech in real-world settings.”

Grok acknowledged that real-world audio is particularly hard to transcribe. But the company is thrilled with its new language model.

The tech giant explained: “Most transcription models do well on clean, single-speaker audio. Real-world audio is harder: flaky phone lines, competing voices, local accents, and phone numbers or email addresses read aloud. We built Grok Voice Transcribe 2.0 for the hardest audio across conditions and environments.

“On the public Artificial Analysis leaderboard, Grok Voice Transcribe 2.0 ranks first for accuracy among 32 streaming models.”

Grok Voice Transcribe 2.0 is also multi-lingual, with the innovation being described as the “largest improvement over Grok Voice Transcribe 1.0”.

Grok shared: “Grok Voice Transcribe 2.0 transcribes dozens of languages, detects the language automatically, and follows mid-recording switches in a single pass. Multilingual accuracy is its largest improvement over Grok Voice Transcribe 1.0.”