Log in
TechniqueBy HypernaturalVersion 6, updated

Gemini ranks voices

hn/gemini-rank-voices

Have Gemini listen to candidate voices' ElevenLabs library previews next to the character's images and rank them by fit, 1 to 10, with what it actually heard. A noisy listener: use it to narrow a shortlist to the 3 worth auditioning and to annotate the review, then let the person pick. Use only when the person wants a voice matched to a face or a detailed character; a plain request ("a British woman") skips it and auditions 3 picked on metadata.

SKILL.md

Give it the character's images, the casting brief and a set of voices (each with its library preview) and you get every voice rated for fit from 1 to 10, best first, with what the voice sounds like, its strengths and its problems. It is one listener's opinion and a noisy one: it decides which 3 voices get auditioned and gives the person notes, but the person picks. It is for matching a voice to a face or a detailed character; for a plain request (guide-cast-a-voice), skip it and audition 3 picked on metadata.

Inputs

  • The pass's brief.json (from elevenlabs-voice-search), with its audition passage.
  • The character images.
  • Per voice: voice_id, library name, previews/<voice_id>.mp3.

Run it

Build one request from references/listening-prompt.md: one user turn of ordered parts (instructions, images, then per voice its label and preview, then the brief and the audition passage) and the response schema there. Images and audio are local paths; the engine uploads them. Find the model's id with models("gemini") and describe it before the first run in a job (earlier jobs used gemini/gemini-3.1-pro-preview):

run("<gemini id>", {
  "contents": [{"role": "user", "parts": [
    {"text": "<instructions>"},
    {"fileData": {"mimeType": "image/jpeg", "fileUri": "<pass>/images/front.jpg"}},
    {"text": "Voice 1: voice_id=<voice_id> (<library name>)"},
    {"text": "Library preview:"},
    {"fileData": {"mimeType": "audio/mpeg", "fileUri": "<pass>/previews/<voice_id>.mp3"}},
    …,
    {"text": "<closing text>"}]}],
  "generationConfig": {"responseMimeType": "application/json",
                       "responseSchema": <the schema in references/listening-prompt.md>}},
  into="<pass>", unit="preview_ratings")

The gateway's Gemini adapter is being built in hn4a; describe gives its exact fields.

One listen per pass: the whole shortlist (12) in one call, previews only, no TTS spent. Save as preview_ratings.json. Drop any voice_id that wasn't sent and any duplicate, and sort by fit, highest first. The top 3 are auditioned on the passage (elevenlabs-tts-v4); the person listens to those, so there is no second listen.

What you get

ratings: per voice voice_id, heard, fit (8 and up means it would cast it), strengths, problems. Put the top 3 to the person with review_choose, each voice an option with its audition and preview as its files and the listener's notes as its text, and the casting brief in brief; the person picks one or writes a note for another pass. Record the pick, its voice id and its performance guide where you keep the job's notes.

Tips and traps

  • The listener is noisy. One voice went from 9/10 to 4/10 between two runs, and the director picked voices it had ranked 3rd and 4th. Never cast from the ranking alone.
  • Previews rank worse than auditions: a weak voice can make the top 3. Audition 3, never more, and let the person hear them. If none fits, the person's note starts another pass, or they ask to hear the next 3.
  • Some voices degrade under eleven_v4 (the audition doesn't sound like the preview). Asked whether two clips are the same voice, Gemini was inconclusive (5 to 7 out of 10 for every variant). The person hears it in the review.
  • It judges by ear, not by the name: it marked down a polished corporate-tutorial read and voices that sounded younger than the face.
  • A different shortlist means a new listen; don't reuse preview_ratings.json.

Check it

Every voice sent comes back rated once; heard describes sound (pitch, texture, age, accent, delivery) rather than repeating the library description.

FAQs

Have Gemini listen to candidate voices' ElevenLabs library previews next to the character's images and rank them by fit, 1 to 10, with what it actually heard. A noisy listener: use it to narrow a shortlist to the 3 worth auditioning and to annotate the review, then let the person pick. Use only when the person wants a voice matched to a face or a detailed character; a plain request ("a British woman") skips it and auditions 3 picked on metadata.

Install Hypernatural Desktop, a free Mac app, and connect it to Claude Code, Codex or Claude Desktop. Then describe the video you want and your agent finds the skill itself, or paste this page's link (https://hypernatural.ai/skill/hn/gemini-rank-voices) and it installs hn/gemini-rank-voices and follows it.

It runs gemini/gemini-3.1-pro-preview. Hypernatural Desktop has every one of them built in, so there are no API keys to set up, though you can bring your own.

The skill is free. You only pay for the AI generations it runs, and your agent shows you the price of every batch before it spends anything. Editing, captions and titles run on your Mac at no cost.

Yes. Ask your agent to adjust it for your job, or to save its own version. You can publish your version under your own handle so anyone can install it.

Go make something cool.

Install the app, open your agent, describe the video. That's the whole onboarding.

Sticker HypernaturalSticker BannerSticker TVBoy