Text-to-speech Sourced statement
Pocket TTS on NVIDIA GPU, 12–16 GB VRAM
Benchmark pending. We haven't measured this pair yet. Below is what the sources say about this hardware, quoted with links.
Mid-range. Most open TTS/STT models fit in fp16; LLM-based TTS at 3–4B may need 16 GB.
EvidenceSourced statement
Commercial useYes
Licensecc-by-4.0
Stated memoryNot stated
Device memory12–16 GB VRAM
Results
Benchmark pending. No measured numbers from us yet for Pocket TTS on 12–16 GB GPU. Get notified or send us your numbers (with the method).
What the sources say about 12–16 GB GPU
- Model authors On a VM with a Tesla T4 (16 GB), moving the model to GPU gave ~2.6x speedup over CPU (~6.28x real time on GPU vs ~2.3–2.5x on CPU). On CPUs with strong single-thread performance the authors saw no GPU speedup. sourceCaveat: Tesla T4 is a datacenter card in the 16 GB class
Method
We haven't run this pair. Everything on this page is quoted from the linked sources, with the source type labelled (model authors vs third parties). Vendor numbers are often measured under favourable conditions.
Ways to run Pocket TTS
Run it
pip install pocket-tts # Linux: add --extra-index-url https://download.pytorch.org/whl/cpu to skip CUDA wheels
pocket-tts generateCopied from the linked README. We haven't run it on this device.
Caveats
- Tesla T4 is a datacenter card in the 16 GB class