Voice

alpha 0.3.0-alpha.2

Preview documentation for @wf/voice@0.3.0-alpha.2. Existing legacy downloads may use a different API; this page does not announce a new release.

Join the alpha Sign in with Google, then add your name. We review alpha access requests.

# Relative paths resolve beside this file; model preparation is explicit.
version: 1
cacheDir: ~/.workforce/models/voice
numThreads: 2
defaults:
  engine: kokoro
  speed: 1
allowPaid: false
allowNonCommercial: false
# Paid engines also need a host-resolved secret reference.
# openaiCredentialRef: OPENAI_API_KEY
# Breeze-TTS-2 uses a separately started Linux/CUDA server, not a model download.
# Noncommercial projects must explicitly set allowNonCommercial: true before
# selecting breeze. prepare() checks the server's health.
# Its model weights and self-hosted outputs are research/noncommercial only.
# breeze:
#   baseUrl: http://127.0.0.1:7860