Creator shares the actual ElevenLabs prompts behind his Seedance dialogue short
DavidmComfort · x · 2026-11-05
DavidmComfort publishes the real prompts from convgen.py for segment G2: one spec generates both the ElevenLabs text-to-dialogue call (elevenv4, stability 0.5, both cast voices in speaking order) and the Seedance video prompt.
Each line is a separate turn with a short voice tag ([softly, matter-of-fact, reasonable], etc.). Practical detail: the finished track must be split at silences and re-spaced in post, because pause tags only buy about 1.7s of pause.
More from Multimodal
- VA-TDM: Velocity Adversarial Distillation Sets SOTA for Few-Step Diffusion Models — Yihong Luo · 2026-11-05
- AI-generated anime music video 'Jealousy' showcases cinematic AI animation — Few_Beautiful2589 · 2026-11-05
- 31.7MB Open-Weights TTS Model Woof Powers an Entire Browser Game, Fully On-Device via WebGPU — brandon_xyzw · 2026-11-05
- CapCut AI fills an unfilmable ad shot with a reference-frame workflow — JaynitMakwana · 2026-11-05
- Veo-generated simulated flight over Mars, built from NASA imagery with original score — DarkMatterProd_ · 2026-11-05
- FrankenSim's physics-based flute synthesis gets graded against real recordings — doodlestein · 2026-11-05