# Ai Text To Speech

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-godot-fun-godot-framework-ai-text-to-speech`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [godot-fun](https://agentstack.voostack.com/s/godot-fun)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [godot-fun](https://github.com/godot-fun)
- **Source:** https://github.com/godot-fun/godot-framework/tree/main/.cursor/skills/ai-text-to-speech

## Install

```sh
agentstack add skill-godot-fun-godot-framework-ai-text-to-speech
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# AI Text-to-Speech (IndexTTS2)

Clone a speaker from a **reference audio**, then synthesize speech from **text** with **[IndexTTS2](https://github.com/index-tts/index-tts)**.

## Rules

When this skill applies, read and follow [skill-dependency-manager](../../rules/skill-dependency-manager.md) — run scripts as documented, install missing tools into `.dependency/`.

- Run `tts.py` through the **`index-tts` manifest entry** (`.dependency/index-tts/.venv/`). Never use host `python`, `py`, `python3`, or any interpreter outside `.dependency/`.
- Do not hand-write IndexTTS Python snippets or `uv run webui.py` for synthesis — use the bundled script.
- IndexTTS **requires `uv`** for install (`pip`/`conda` are unsupported upstream). Python must be **`>=3.10,/tts/speech.wav`):

```bash
.dependency/index-tts/.venv/Scripts/python.exe .cursor/skills/ai-text-to-speech/scripts/tts.py \
  --voice audio/voice/ref.wav \
  --text "你好，欢迎来到这个世界。"
# → audio/voice/tts/speech.wav
```

Explicit output path:

```bash
.dependency/index-tts/.venv/Scripts/python.exe .cursor/skills/ai-text-to-speech/scripts/tts.py \
  --voice audio/voice/ref.wav \
  --text "Hello, this is a test." \
  --output audio/voice/tts/hello.wav
```

Long script from a UTF-8 text file:

```bash
.dependency/index-tts/.venv/Scripts/python.exe .cursor/skills/ai-text-to-speech/scripts/tts.py \
  --voice audio/voice/ref.wav \
  --text-file script/lines/intro.txt \
  --output audio/voice/tts/intro.wav
```

FP16 (faster, less VRAM):

```bash
.dependency/index-tts/.venv/Scripts/python.exe .cursor/skills/ai-text-to-speech/scripts/tts.py \
  --voice audio/voice/ref.wav \
  --text "测试半精度推理。" \
  --fp16
```

## Emotion control (optional)

| Mode | Flags | Notes |
|------|-------|-------|
| Emotion reference audio | `--emotion-audio path.wav` | Separate clip for emotion; timbre still from `--voice` |
| Emotion weight | `--emotion-weight 0.6` | Maps to `emo_alpha` (`0.0`–`1.0`, default `1.0`) |
| Emotion from text | `--emotion-from-text` | Infer emotion from synthesis text; prefer `--emotion-weight` ≈ `0.6` |
| Emotion description | `--emotion-text "..."` | Natural-language emotion; implies text emotion mode |
| Emotion vector | `--emotion-vector 0,0,0.8,0,0,0,0,0` | 8 floats: happy, angry, sad, afraid, disgusted, melancholic, surprised, calm |

```bash
# Emotion reference audio
.dependency/index-tts/.venv/Scripts/python.exe .cursor/skills/ai-text-to-speech/scripts/tts.py \
  --voice audio/voice/ref.wav \
  --emotion-audio audio/voice/emo_sad.wav \
  --emotion-weight 0.9 \
  --text "酒楼丧尽天良，开始借机竞拍房间。" \
  --output audio/voice/tts/sad_line.wav

# Emotion description text
.dependency/index-tts/.venv/Scripts/python.exe .cursor/skills/ai-text-to-speech/scripts/tts.py \
  --voice audio/voice/ref.wav \
  --emotion-text "害怕、紧张" \
  --emotion-weight 0.6 \
  --text "快躲起来！是他要来了！" \
  --output audio/voice/tts/afraid_line.wav
```

Do not combine `--emotion-audio`, `--emotion-vector`, and `--emotion-text` / `--emotion-from-text` in conflicting ways — pick one emotion source.

## Defaults

| Option | Default | Notes |
|--------|---------|-------|
| Output | `/tts/speech.wav` | Auto-create `tts/`; use `--output` to override |
| Model | `.dependency/index-tts/checkpoints` | IndexTTS-2 |
| `--fp16` | off | Enable on GPU when VRAM is tight |
| `--emotion-weight` | `1.0` | Lower (~0.6) for text emotion modes |
| Overwrite | off | Pass `--force` to replace an existing output |

## Agent workflow

1. **Confirm inputs** — need a clear reference voice WAV/MP3 and the text (or `--text-file`). Ask if either is missing.
2. **Use the user's real paths** — do not copy voice files into the repo unless asked.
3. **Trial first** — synthesize one short line, play/inspect before long scripts.
4. **Reference audio tips** — clean, single-speaker, little noise; a few seconds of clear speech works best.
5. **Missing install** — follow **Setup**; register `index-tts` in `manifest.json`; retry the same command.
6. **GPU** — prefer CUDA + `--fp16` for speed; CPU is acceptable for short tests only.
7. **Revert** — delete files under `tts/`; sources are never modified.

## Troubleshooting

| Issue | Fix |
|-------|-----|
| `index-tts` not populated | Clone + `uv sync` + download checkpoints; update manifest |
| `checkpoints/config.yaml` missing | Re-run `hf download IndexTeam/IndexTTS-2 --local-dir=checkpoints` |
| CUDA / torch errors | Install CUDA 12.8+; or run on CPU (slow) |
| OOM / VRAM | Pass `--fp16`; shorten text; close other GPU apps |
| Slow HuggingFace | Set `HF_ENDPOINT=https://hf-mirror.com`; or use ModelScope |
| `uv sync` / DeepSpeed fail on Windows | Use `uv sync --extra webui` without deepspeed |
| Unnatural emotion | Lower `--emotion-weight` to ~0.6; try a clearer `--emotion-audio` |

## Related

- Upstream: https://github.com/index-tts/index-tts
- Models: [IndexTTS-2 (HuggingFace)](https://huggingface.co/IndexTeam/IndexTTS-2)
- Post-process loudness / format: [audio-loudness-normalization](../audio-loudness-normalization/SKILL.md), [audio-to-ogg](../audio-to-ogg/SKILL.md), [audio-to-wav](../audio-to-wav/SKILL.md)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [godot-fun](https://github.com/godot-fun)
- **Source:** [godot-fun/godot-framework](https://github.com/godot-fun/godot-framework)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-godot-fun-godot-framework-ai-text-to-speech
- Seller: https://agentstack.voostack.com/s/godot-fun
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.