agentleFS
badgidsbadgids/Story-Film-Skills/skills/qwen3-tts/SKILL.md

qwen3-tts

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Adapt voice cues into Qwen3 TTS custom-voice, voice-design, or voice-clone inputs, preserving exact dialogue, language, character voice identity, delivery instruction, and reusable clone references.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use a supported predefined speaker plus optional natural-language instruct control for delivery.

    line 15
  2. Distinctive:

    Use the 1.7B VoiceDesign model to create a new voice from a natural-language description.

    line 21
  3. Very specific:

    Use a Base model with reference audio.

    line 29
  4. Distinctive:

    Never paraphrase a screenplay line without updating the screenplay.

    line 44
  5. Distinctive:

    Keep delivery instructions playable and audible.

    line 46
  6. Distinctive:

    Every output contains enough information to reproduce the intended speaker identity and exact line without reading the screenplay again.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Qwen3 TTS Prompting

Choose mode

CustomVoice

Use a supported predefined speaker plus optional natural-language instruct control for delivery.

Required fields: text, language, speaker. Optional: instruct.

VoiceDesign

Use the 1.7B VoiceDesign model to create a new voice from a natural-language description.

Required fields: text, language, instruct.

The instruction should describe audible traits such as approximate vocal age, register, timbre, cadence, articulation, breath, accent only when decided, and delivery behavior. Avoid visual personality traits that cannot be heard.

VoiceClone

Use a Base model with reference audio. For highest identity consistency, provide ref_audio and accurate ref_text. Speaker-vector-only mode can work without reference text but may reduce cloning fidelity.

For an invented recurring character, a practical pipeline is:

  1. VoiceDesign a clean short reference.
  2. Save the exact reference transcript.
  3. Build a reusable clone prompt from that reference.
  4. Generate later lines from the reusable clone identity.

Output

Save one JSON object per cue under 04_generation/prompts/qwen3-tts/ or a JSONL batch with exact screenplay text.

Rules

  • Never paraphrase a screenplay line without updating the screenplay.
  • State language explicitly when known.
  • Keep delivery instructions playable and audible.
  • Preserve one VOICE-### mapping per recurring character.

Done

Every output contains enough information to reproduce the intended speaker identity and exact line without reading the screenplay again.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.