# Voice tests with maps and a presenter > A Japanese voice-model comparison pairs a studio presenter with dark test cards for emotion, regional dialects and sports commentary. Serif headlines, dotted maps and paired model panels organize the examples. - Kind: Video - Page: https://meetreference.com/v/video-voice-tests-with-maps-and-a-presenter-98c324/ - Ready-to-use agent handoff: https://meetreference.com/v/video-voice-tests-with-maps-and-a-presenter-98c324/agent.txt - Authorship: AI-made, per the source - Made with: Claude Code, Codex - Model: Opus 5.5, Elevenlabs Eleven v4, Gemini 3.8 Flash TTD, GPT-Image-2.5, LTX 2.3 - Built with: Hyperframes - Services: Epidemic Sound, Colab CLI - Style: Explainers; presenter-led, editorial, cinematic, typographic, minimal-interface - Length and format: 5 min, 16:9 (1280x720 source) - Playback: a muted visual reference. The original soundtrack is available only at the source. - Shared by @nakazakifam in X, Sep 29, 2026: https://x.com/nakazakifam/status/2104803180877906110 - Prompt fidelity: Unavailable in this entry. The recreation brief is written by Reference. ## Before you start Guidance from Reference, separate from the creator's instructions. 1. Read the reference and inspect the project, installed libraries, and available agent skills before writing code. Reuse suitable tools already present. 2. Prefer the creator-reported libraries and skills when they fit the task. Explain what useful additions help with, and install missing project dependencies or relevant skills from official sources when the environment and the user's existing permissions allow it. Respect the project's package manager and setup rules; do not ask again for routine setup already authorized. 3. Distinguish tools used by the creator from your own recommendations. A listed tool is not automatically required, and an empty tools or requirements list means the setup is unknown, not that nothing is needed. 4. Ask concise questions when missing inputs or choices materially affect the result: paid services, credentials, the user's assets, or a different production approach. Use existing answers and permissions; continue independent work while waiting. 5. If a useful library, skill, or service cannot be installed or used, explain an available alternative and its expected effect on quality, features, or effort. Get the user's choice before a material compromise; otherwise state the fallback and continue. Never silently simplify the result or claim to have used a tool you did not use. ## Recreating this video This is a visual reference. No original creator prompt is available. The following brief was written by Reference after inspecting the work. Adapt this format to compare two approaches to another subject, alternating a welcoming presenter setting with restrained editorial example cards. Give each test a large heading and a relevant visual, such as a map or location image. Keep paired comparison labels in the same bottom positions and use two accent colors to distinguish the alternatives. 1. Open the live work or source and inspect the frame images below. 2. Adapt its layout, hierarchy, palette, and interaction patterns to the user's own content and brand. 3. Compare the result against the reference. Use your own assets and credit the original creator. ## What it looks like Written by Reference from the video frames, not by the creator. A polished presenter-led explainer featuring a woman in a warm studio alongside dark, data-focused comparison graphics. - Color: Warm beige and wood tones with leafy greens in the studio; charcoal and black panels with white text and teal accents in the graphics. - Type: Clean, modern Japanese typography, with prominent white headings and smaller labels. - Framing: The presenter is centered in a medium shot with a large microphone at the right. Separate graphics use spacious layouts, maps, chart marks, and labeled service panels. - Structure: Alternates between the studio presenter and minimal comparison slides, including Japanese dialect examples, ElevenLabs and Gemini TTS labels, and a sports-themed graphic. Storyboard, nine frames spread across the video: https://meetreference.com/media/video-voice-tests-with-maps-and-a-presenter-98c324/storyboard.webp - Frame 1 at 17.3s: https://meetreference.com/media/video-voice-tests-with-maps-and-a-presenter-98c324/f1.webp - Frame 2 at 52.0s: https://meetreference.com/media/video-voice-tests-with-maps-and-a-presenter-98c324/f2.webp - Frame 3 at 86.7s: https://meetreference.com/media/video-voice-tests-with-maps-and-a-presenter-98c324/f3.webp - Frame 4 at 121.3s: https://meetreference.com/media/video-voice-tests-with-maps-and-a-presenter-98c324/f4.webp - Frame 5 at 156.0s: https://meetreference.com/media/video-voice-tests-with-maps-and-a-presenter-98c324/f5.webp - Frame 6 at 190.7s: https://meetreference.com/media/video-voice-tests-with-maps-and-a-presenter-98c324/f6.webp - Frame 7 at 225.3s: https://meetreference.com/media/video-voice-tests-with-maps-and-a-presenter-98c324/f7.webp - Frame 8 at 260.0s: https://meetreference.com/media/video-voice-tests-with-maps-and-a-presenter-98c324/f8.webp - Frame 9 at 294.7s: https://meetreference.com/media/video-voice-tests-with-maps-and-a-presenter-98c324/f9.webp ## Links - Watch: https://x.com/nakazakifam/status/2104803180877906110 - Original post: https://x.com/nakazakifam/status/2104803180877906110 - Discovery collection: https://data.openchamber.dev/opus-5-5-videos/v/nakazakifam-2104803180877906110