Vertical explainer on Gemini voice cloning in two languages
34.8K views·228 likes·250 saves·27 reposts·Posted 26 Sept 2026 · 0:57 · Production
Our note
A vertical Japanese short reviewing Gemini 3.8 Flash TTS voice cloning, with EN and Chinese speech cards; Opus 5.5 made the diagram animation, Gemini TTS the voice, Seedance the opening.
The creator’s post
【検証】Gemini 3.8 Flash TTSで、自分の声をクローンしてみた 結論、クローンの精度が高い。個人的には、ElevenLabsの有料のプロ向けクローンよりも良いかなと思いました。（普通の読み上げは3.1 Flash時点でも精度高かったので、まあまあという印象でした。） ・約24秒話して、同意文を読むだけで声をコピー ・英語も中国語も、自分の声のまま話せる ・標準の声は前のモデルから優秀で、そこは大差なし 私は動画作成で音声をめちゃくちゃ使うので、かなり重宝してます。 今回の図解アニメはClaude Opus 5.5、声はGemini 3.8 Flash TTS、冒頭の顔と声はSeedance 2.5。この3つで、大体のショート動画は精度高く作れるかなと。
The prompt
The creator didn’t publish a prompt for this one. Start from the prompt template instead.
Make one like this
1 · Start from a template
This creator didn't share a prompt. Start from the template and describe this video's look.
2 · Direct it like an editor
Ask for one self-contained HTML file on a fixed 1920×1080 stage, link this video as the reference, and send two or three rounds of specific notes.
3 · Render it to MP4
Screen-record a short piece, or capture it frame by frame for exact timing. How →
How it was made
The creator didn’t name their tools. Most videos like this are HTML, canvas or SVG animation written by Claude and screen-recorded or rendered to MP4. How that works →
Look
Views as of collection. Video, post and prompt © their creator.
Create with Zryth