Tools and Setup

Back to Video Stack - Overview

Paths on TonyB

C:\tts\tts.py - Chatterbox voice script (--ref <wav> for cloning)
C:\tts\gemini_tts.py - Gemini TTS; --style for directions, --whole (whole script in one request), --fallback-model (switch to Lite when the daily limit is hit)
C:\tts\qwen3tts - Qwen3-TTS venv (1.7B VoiceDesign / Base clone)
C:\tts\chatterbox - Chatterbox venv
C:\tts\voices\user_announcer_ref.wav - user's own announcer recording (20.65 s, mono 24 kHz)
C:\tts\vt\vt.py - voice-test runner
C:\video\template - video template
C:\video\HERMES_PROMPT.md, C:\video\COPYWRITING.md
C:\video\examples\prop1ad - worked example
C:\video\voice_tests - bake-off samples
Hermes profile: C:\Users\fight\AppData\Local\hermes\profiles\explainer - start with explainer chat

Qwen llama-server on :1922 uses ~6.4 GB baseline. Never start Gemma (:1923) alongside it.
Peak VRAM seen: Chatterbox 3.9 GB, Qwen3-TTS VoiceDesign ~4.3-4.5 GB, Qwen3-TTS clone 5.0 GB. Run TTS models one at a time.
Long runs: one-time scheduled tasks (schtasks /create ... /sc once, /run), delete afterwards.

Free tier: 10 requests/day on flash-tts (resets ~4:50 PM PT); flash-lite-tts 3/min. Script auto-falls back to Lite.
Style must go in speech_metadata.style (interactions endpoint), never in the text.
GEMINI_API_KEY goes in the explainer profile .env (user step; not confirmed done).

Install: C:\Users\fight\Projects\ACE-Step-1.5 (v1.5.0, commit ca1e85f, .venv). License MIT (code + weights): commercial use OK.
Models: acestep-v15-turbo DiT + acestep-5Hz-lm-0.6B (1.7B LM also on disk, unused).
Server: scheduled task ACEStepServer -> start_acestep_api.bat -> Gradio UI + REST API at http://127.0.0.1:7860 (/health, /release_task, /query_result). Log: acestep_server.log. Restart: schtasks /Run /TN ACEStepServer (~80 s to load). Does not start at boot.
Wrapper: C:\Users\fight\Projects\ACE-Step-1.5\.venv\Scripts\python.exe C:\tts\acestep_music.py --prompt "<tags>, no vocals" --duration 47 [--bpm N --key "D minor" --seed N] --out <path-no-ext> -> full mp3 + 20 s preview at -18 LUFS.
Speed: 22-30 s per 45 s instrumental. VRAM: shares the 3060 with Qwen (1922); peak ~11.7/12 GB during generation (CPU offload on). Don't run it at the same time as Qwen3-TTS/Chatterbox.
Test tracks: C:\video\music\acestep\acestep_business.mp3, acestep_political.mp3.
Fallbacks: code-synth scripts/music/gen.py/gen2.py; ElevenLabs el_music.py (optional, paid).