freedak/OpenMontage
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Default TTS recommendation to Google Chirp3-HD over ElevenLabs

Browse Source 
Chirp3-HD is near-free ($0.003 vs $0.30+ per script), expressive,
24kHz, and available without quota limits. ElevenLabs demoted to
voice-cloning-only recommendation.
This commit is contained in:
calesthio
2026-04-04 14:08:34 -07:00
parent 20dcc785e5
commit 370f2f11b7
1 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/meta/video-reference-analyst.md
+5 -3
View File
@@ -210,9 +210,11 @@ Use this structure for each variant:
- Audio architecture: [single narrator / character dialogue / narrator + characters]
- Voice casting: [voice name + ID for each role — narrator, character A, etc.]
- TTS provider: [selected from available providers via tts_selector preflight —
ElevenLabs (premium), Google TTS (affordable, multilingual), OpenAI TTS
(solid fallback), Piper (offline/free). Do NOT hardcode a provider — run
preflight to check what's configured and recommend the best available.]
Google Chirp3-HD (best value: near-free, expressive, 24kHz),
ElevenLabs (voice cloning only), OpenAI gpt-4o-mini-tts (good with
instructions param), Piper (offline/free). Do NOT hardcode a provider —
run preflight to check what's configured and recommend the best available.
**Default recommendation: Google Chirp3-HD** unless voice cloning is needed.]
- Music: [library track / generated / none]
- Sound design: [any special audio needs]