Transcribing audio to text using ASR models like Whisper for production transcription pipelines. The L40S has 48 GB of GPU memory against a 8 GB minimum for this workload.
The GPU's published specification against the workload's stated minimum.
Listing-weighted median across 4 observed L40S listings at Verda. The same GPU is tracked at 13 marketplaces total.
The 5 lowest-priced other marketplaces listing the same GPU, sorted by price ascending.
Other GPUs at Verda that meet Speech-to-Text's minimum GPU memory, sorted by price ascending.
Transcribing audio to text using ASR models like Whisper for production transcription pipelines. Speech-to-Text requires at least 8 GB VRAM and benefits from Datacenter or Workstation or Consumer-class compute.
Full Speech-to-Text guide and the GPUs that meet its minimumTrack L40S rental pricing at Verda, updated daily — useful for sustained speech-to-text workloads.