Breeze TTS 2 studio

loading… OpenAPI /docs

Presets are just saved instructions — the model has no built-in speaker list.

1 = ignore the instruction · 4 = recommended · 8+ = stiff

Same seed + same text = same audio

Alt seeds (child / elderly pacing varies a lot by take)

WAV is always kept on the server

Result

Nothing generated yet. Pick a preset, type a line, hit Generate.

What to expect on this box

  • Fast path (CUDA graphs): TTFA ≈ 0.23 s, generation ≈ 1.66× realtime — a 20 s clip takes ~33 s.
  • 24 kHz mono output, ≤ 120 s of audio per request (longer text is cut at the token cap).
  • One GPU slot: extra requests queue here, raw /v1/* callers get 409.
  • Elderly / child voices speak slower — same text, ~1.7× the duration.

History

raw
loading…