Grok Voice Transcribe 2.0 update improves short-phrase speech recognition

The latest speech-to-text update introduces significant accuracy gains for short phrases, alongside new features like word-level timestamps and speaker diarization.

2 min read

Graphic title card for Grok Voice Transcribe 2.0 with an orange and purple background.
Introducing Grok Voice Transcribe 2.0, the latest speech-to-text update.

A new speech-to-text release aims to solve common hurdles in audio transcription, particularly when dealing with brief utterances that lack surrounding context.

Key facts

Audio Duration
8 hours
AA-AgentTalk Weight
50%
VoxPopuli Weight
25%
Earnings22 Weight
25%

Accuracy and short phrases

Short phrases, such as in-car commands, often give transcription systems little context to correctly identify the spoken language. On a dedicated short-phrase test set, the word error rate drops from 20.6% to 6.8% in this update.

Features and capabilities

Existing speech-to-text application programming interfaces — the software bridges that let different programs talk to each other — receive the accuracy improvements with no code changes needed for batch or streaming modes. Users can transcribe recorded files and URLs, or process live audio streams in real time.

The system includes several advanced controls:

  • Word-level timestamps providing precise start and end times alongside confidence scores.
  • Speaker diarization to label individual speakers in a transcript at no additional cost.
  • Multichannel transcription supporting up to 8 independent audio channels.
  • Key term biasing, which lets developers pass up to 100 domain-specific terms like medical vocabulary per request.
  • Automated text formatting that converts numbers, dates, currencies, and emails into written form.
  • Filler word removal to omit vocal pauses like "um" and "uh".
  • Smart turn detection to identify the end of a speaker's turn for voice-based agents.

Real-world adoption and pricing

Atlassian Loom now uses the technology for video transcriptions, finding it more accurate than previous solutions. This accuracy enables new workflows, such as recording an action plan and piping the resulting transcript directly into code editors like Cursor.

Product interface screenshot demonstrating video transcription and bug report generation workflows.
Loom interface showing video recording and automated transcription workflows., Source ↗

Pricing remains unchanged from the previous version. Batch transcription costs $0.10 per hour of audio, while streaming costs $0.20 per hour, with diarization, timestamps, and key terms included.

Source: Original announcement

Worth a read?

Report

Comments