Public KG record
Cartesia Ink-2
Recorded overview
Competing speech transcription model evaluated on streaming WER and pricing.
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: AA-WER Streaming
- Performance: 3.4% at 0.43s with semantic endpoints
- Performance: 4.0% at 0.07s with external endpoints
- Performance: 最终转录延迟0.07秒，WER 4.0%
- Performance: 4.0% WER、0.07秒到最终转录
- Pricing: $4.00 per 1,000 audio minutes
Evidence coverage
The KG currently records 8 known information dimensions and has 10 undocumented dimensions, linked to 2 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Muse Voice Transcribe — competes with
- AA-WER Streaming — evaluated on
- Muse Voice Transcribe — competes with