Synthesize
- 70 installs
- 62 repo stars
- Updated August 3, 2026
- terrylica/cc-skills
Helps with ai & agent building tasks.
About
synthesize is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted development.
- synthesize
- AI & Agent Building
- AI-coding skill
Synthesize by the numbers
- 70 all-time installs (skills.sh)
- Ranked #5,726 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/terrylica/cc-skills --skill synthesizeAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 70 |
|---|---|
| repo stars | ★ 62 |
| Last updated | August 3, 2026 |
| Repository | terrylica/cc-skills ↗ |
What it does
Helps with ai & agent building tasks.
Files
Synthesize Speech
Generate speech from text using the Kokoro TTS CLI tool. Supports single WAV output or chunked streaming for long text.
Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.
Quick Usage
# Single WAV
~/.local/share/kokoro/.venv/bin/python ~/.local/share/kokoro/tts_generate.py \
--text "Hello from Kokoro TTS" --voice af_heart --lang en-us --speed 1.0 \
--output /tmp/kokoro-tts-$$.wav
# Play it
afplay /tmp/kokoro-tts-$$.wavParameters
| Parameter | Default | Description |
|---|---|---|
--text | (required) | Text to synthesize |
--voice | af_heart | Voice name (see voice catalog) |
--lang | en-us | Language code (en-us, zh, ja, etc.) |
--speed | 1.0 | Speech speed multiplier |
--output | (required) | Output WAV path |
--chunk | off | Chunked streaming mode for long text |
Voice Catalog
See Voice Catalog for all available voices with quality grades.
Top voices:
| Voice ID | Name | Grade | Gender |
|---|---|---|---|
| af_heart | Heart | A | Female |
| af_bella | Bella | A- | Female |
| af_nicole | Nicole | B- | Female |
Chunked Streaming
For long text, use --chunk to get progressive playback:
~/.local/share/kokoro/.venv/bin/python ~/.local/share/kokoro/tts_generate.py \
--text "Long text here..." --voice af_heart --lang en-us --speed 1.0 \
--output /tmp/kokoro-tts-$$.wav --chunkEach chunk WAV path is printed to stdout as it becomes ready. The final line is DONE <ms>.
Troubleshooting
| Issue | Cause | Solution |
|---|---|---|
| No audio output | Model not loaded | Run /kokoro-tts:install first |
| Empty text error | Input was blank | Provide non-empty --text |
| Slow generation | First-run warmup | Normal — subsequent runs faster |
Post-Execution Reflection
After this skill completes, check before closing:
1. Did the command succeed? — If not, fix the instruction or error table that caused the failure. 2. Did parameters or output change? — If the underlying tool's interface drifted, update Usage examples and Parameters table to match. 3. Was a workaround needed? — If you had to improvise (different flags, extra steps), update this SKILL.md so the next invocation doesn't need the same workaround.
Only update if the issue is real and reproducible — not speculative.
Kokoro Voice Catalog
Complete list of available Kokoro TTS voices with quality grades.
English Voices
Female
| Voice ID | Name | Grade | Characteristics |
|---|---|---|---|
| af_heart | Heart | A | Warm, natural, excellent prosody. Best overall voice. |
| af_bella | Bella | A- | Clear, professional. Slight robotic edge in long text. |
| af_nicole | Nicole | B- | Expressive but inconsistent pacing. |
| af_aoede | Aoede | C+ | Musical quality but lacks clarity in speech. |
| af_kore | Kore | C+ | Decent but unremarkable. |
| af_sarah | Sarah | C+ | Adequate, slightly breathy. |
Male
| Voice ID | Name | Grade | Characteristics |
|---|---|---|---|
| am_adam | Adam | F+ | Artificial, poor prosody. |
| am_michael | Michael | unrated | Newer voice, not yet graded. |
| am_echo | Echo | D | Robotic, monotone. |
| am_puck | Puck | unrated | Newer voice, not yet graded. |
Chinese Voices
| Voice ID | Name | Grade | Characteristics |
|---|---|---|---|
| zf_xiaobei | Xiaobei | unrated | Default Chinese voice. |
Grade Scale
| Grade | Meaning |
|---|---|
| A | Excellent — natural, clear, great prosody |
| A- | Very good — minor artifacts |
| B- | Decent — noticeable but acceptable issues |
| C+ | Acceptable — some quality concerns |
| D | Poor — robotic or monotone |
| F+ | Failing — barely usable |
Recommendations
- English default:
af_heart(Grade A) — best overall quality - Chinese default:
zf_xiaobei— only Chinese voice available - Male voice: None recommended at this time (all grade D or below)
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10