Agent-Skills.md

Agent Skills: Voice Quality Audition

Audition Kokoro TTS voices to compare quality and grade. TRIGGERS - audition voices, kokoro voices, voice comparison, tts voice, voice quality, compare voices.

UncategorizedID: terrylica/cc-skills/voice-quality-audition

Repository

terrylica/cc-skills
terrylicaLicense: MIT
264

Install this agent skill to your local

pnpm dlx add-skill https://github.com/terrylica/cc-skills/tree/HEAD/plugins/tts-tg-sync/skills/voice-quality-audition

Skill Files

Browse the full folder contents for voice-quality-audition.

Download Skill

Loading file tree…

plugins/tts-tg-sync/skills/voice-quality-audition/SKILL.md

Skill Metadata

Name
voice-quality-audition
Description
Audition Kokoro TTS voices to compare quality and grade. TRIGGERS - audition voices, kokoro voices, voice comparison, tts voice, voice quality, compare voices.

Voice Quality Audition

Compare Kokoro TTS voice quality across all available voices. Runs tts_kokoro_audition.sh which plays a passage with each top voice. Each voice announces its name before reading the passage. Uses clipboard text or a default passage.

Platform: macOS (Apple Silicon)

When to Use This Skill

  • Audition all available Kokoro voices to hear quality differences
  • Compare specific voices side-by-side for a project
  • Re-evaluate voice grades after a Kokoro engine upgrade
  • Select a new default voice for TTS_VOICE_EN or TTS_VOICE_ZH
  • Test how a particular passage sounds across multiple voices

Requirements

  • Kokoro TTS engine installed and healthy (kokoro-install.sh --health)
  • Apple Silicon Mac with MLX Metal available
  • afplay available (ships with macOS)
  • Audition script at plugin scripts/tts_kokoro_audition.sh
  • Shared library at plugin scripts/lib/tts-common.sh

Voice Catalog

| Voice ID | Name | Grade | Gender | | ---------- | ------- | ------- | ------ | | af_heart | Heart | A | Female | | af_bella | Bella | A- | Female | | af_nicole | Nicole | B- | Female | | af_aoede | Aoede | C+ | Female | | af_kore | Kore | C+ | Female | | af_sarah | Sarah | C+ | Female | | am_adam | Adam | F+ | Male | | am_michael | Michael | unrated | Male | | am_echo | Echo | D | Male | | am_puck | Puck | unrated | Male |

Current defaults (configured in ~/.claude/automation/claude-telegram-sync/mise.toml):

  • English voice: af_heart (Grade A) via TTS_VOICE_EN
  • Chinese voice: zf_xiaobei via TTS_VOICE_ZH
  • macOS say fallback EN: Samantha via TTS_VOICE_SAY_EN
  • macOS say fallback ZH: Ting-Ting via TTS_VOICE_SAY_ZH

See Voice Catalog for detailed characteristics and grade criteria.

Workflow Phases

Phase 1: Preflight

Verify Kokoro is installed and healthy:

kokoro-install.sh --health

All 6 checks must pass (venv, Python 3.13, mlx_audio importable, kokoro_common.py, tts_generate.py, version.json).

Phase 2: Text Selection

The audition script reads from the macOS clipboard (pbpaste). If the clipboard is empty or not text, it falls back to a built-in passage about reading in a library.

To audition with custom text, copy the desired passage to the clipboard before running.

Phase 3: Ask User — Full or Selective Audition

Use AskUserQuestion to determine scope:

  • Full audition — Play all 10 voices sequentially (takes several minutes)
  • Select specific voices — Run only a subset (e.g., top 3 female voices)

For a selective audition, edit the VOICES array in the script or pass voice IDs manually.

Phase 4: Execute Audition

~/.local/bin/tts_kokoro_audition.sh

Or directly from the plugin source:

/path/to/plugins/tts-tg-sync/scripts/tts_kokoro_audition.sh

The script acquires the TTS lock, plays each voice sequentially with a 1-second gap, then releases the lock on exit.

Phase 5: Feedback

Use AskUserQuestion to collect the user's preference:

  • Which voice sounded best?
  • Any voices to eliminate from future consideration?
  • Should we update grade assignments?

Phase 6: Apply Configuration

Optionally update the default voice in mise.toml:

# ~/.claude/automation/claude-telegram-sync/mise.toml
[env]
TTS_VOICE_EN = "af_heart"   # Change to preferred voice ID
TTS_VOICE_ZH = "zf_xiaobei"

After changing mise.toml, restart the Telegram bot for the new voice to take effect.

TodoWrite Task Templates

1. [Preflight] Verify Kokoro TTS is installed and healthy (kokoro-install.sh --health)
2. [Text] Check clipboard for passage, fall back to default if empty
3. [Select] Ask user: full audition (all 10 voices) or specific voices
4. [Audition] Run tts_kokoro_audition.sh and let user listen
5. [Feedback] Ask user which voice they prefer and collect grade feedback
6. [Apply] Optionally update TTS_VOICE_EN in mise.toml and restart bot

Post-Change Checklist

  • [ ] Kokoro health check passed before audition
  • [ ] All selected voices played without errors
  • [ ] User confirmed preferred voice
  • [ ] mise.toml updated with new voice ID (if changed)
  • [ ] Bot restarted after configuration change (if applicable)
  • [ ] Voice catalog grades updated in reference doc (if re-graded)

Post-Execution Reflection

After this skill completes, reflect before closing the task:

  1. Locate yourself. — Find this SKILL.md's canonical path (Glob for this skill's name) before editing. All corrections target THIS file and its sibling references/ — never other documentation.
  2. What failed? — Fix the instruction that caused it. If it could recur, add it as an anti-pattern.
  3. What worked better than expected? — Promote it to recommended practice. Document why.
  4. What drifted? — Any script, reference, or external dependency that no longer matches reality gets fixed now.
  5. Log it. — Every change gets an evolution-log entry with trigger, fix, and evidence.

Do NOT defer. The next invocation inherits whatever you leave behind.

Troubleshooting

| Issue | Cause | Solution | | ------------------------------- | ---------------------------------- | ----------------------------------------------------------------------- | | No audio plays | Kokoro not installed | Run kokoro-install.sh --install or use full-stack-bootstrap skill | | Audio cuts off mid-sentence | TTS lock stolen by another process | Check for competing TTS processes: pgrep -la afplay | | Voice sounds wrong | Invalid voice ID in Kokoro model | Verify voice ID exists in VOICES array; check Kokoro version | | Clipboard empty | No text copied | Script uses default passage automatically; no action needed | | "ERROR: Local Kokoro not found" | Venv or script missing | Run kokoro-install.sh --health to diagnose; --install to fix | | FAILED for a specific voice | Voice not available in model | Voice may require a different Kokoro version; check model compatibility | | Lock not released | Script crashed without cleanup | Remove stale lock: rm -f /tmp/kokoro-tts.lock | | All voices sound identical | Kokoro model not loaded properly | Re-download model: kokoro-install.sh --upgrade |

Reference Documentation

  • Voice Catalog - Comprehensive voice listing with quality grades, characteristics, and selection guidance
  • Evolution Log - Change history for this skill