TTS

Use this skill whenever the user wants to convert text to speech, generate audio from text, create voiceovers, or produce spoken audio files. Triggers includ...

Security Scan

The skill is internally consistent: it simply documents how to call a third‑party TTS HTTP API and how to save the resulting MP3s, with no extra credentials, installs, or unexpected behavior.

Purpose & Capability

Name/description (text-to-speech) matches the instructions: the SKILL.md describes calling a hosted TTS HTTP API (generate speech, list voices/providers). Nothing requested is unnecessary for that purpose.

Instruction Scope

Instructions direct network calls to https://tts.102465.xyz and instruct saving output files to /mnt/user-data/outputs/. That is expected for a TTS skill, but the skill references a specific system path (not declared in requires.config) and recommends GET URLs (which will embed text in query strings). Both are functional but have privacy/operation implications (text sent to third party; GET leaks text in logs/refs).

Install Mechanism

There is no install spec and no code files — this is instruction-only, so nothing is written to disk by an installer. Lowest-risk install posture.

Credentials

The skill declares no environment variables or credentials and the instructions do not ask for secrets. That is proportionate for a public hosted-API usage model. (Note: absence of an API key implies the service may be public or unauthenticated.)

Persistence & Privilege

Skill is not always-enabled and does not request elevated/persistent privileges. It does suggest writing output files to a user-data directory, which is normal for producing artifacts.

Assessment

This skill appears to do what it says: call a third‑party TTS HTTP API and save MP3 output. Before installing, consider: (1) the API endpoint (tts.102465.xyz) is an unknown third party — any text you synthesize will be sent to that server, so avoid sending sensitive content; (2) GET URLs put text into query strings (may be logged or cached) — prefer POST for private or long text; (3) the instructions write files to /mnt/user-data/outputs/ — ensure you are comfortable with generated files being stored there; (4) no credentials are requested, so the service may be public/unrestricted — if you need audited/enterprise TTS, prefer an official provider or self-hosted alternative. Because this is instruction-only (no code to inspect), if you need higher assurance ask the publisher for an official domain, a privacy policy, or an auditable implementation.

Text-to-Speech (TTS) via tts.102465.xyz

Convert text into spoken audio using a hosted TTS API that supports multiple providers, voices, emotions, and tuning parameters.

API Base URL

https://tts.102465.xyz

All endpoints are under the /api prefix.

Quick Reference

Task	Endpoint	Method
Generate speech audio	/api/tts	POST or GET
List available voices	/api/voices?provider=<name>	GET
List available providers	/api/providers	GET

Generating Speech

Two equivalent ways to call the TTS endpoint:

POST (recommended for longer text or programmatic use)

curl -X POST https://tts.102465.xyz/api/tts \
  -H "Content-Type: application/json" \
  -d '{"text":"你好世界","voice":"晓晓","emotion":"温柔","provider":"azure"}' \
  --output output.mp3

GET (convenient for short text or browser-playable links)

https://tts.102465.xyz/api/tts?text=你好世界&voice=晓晓&provider=azure

The response is an audio file (MP3). Save it with --output in curl, or open the GET URL directly in a browser to play.

Parameters

Parameter	Description	Default
text	Text to synthesize (required)	—
voice	Voice name (Chinese label or English ID)	Provider default
emotion	Emotion or speaking style (Azure only)	—
rate	Speech rate adjustment, percentage (Azure/Edge)	0
pitch	Pitch adjustment, percentage (Azure/Edge)	0
provider	TTS backend: azure, volcengine, or edge	azure

Providers at a Glance

• azure — Default provider. Richest feature set: many voices, emotion/style control, rate and pitch tuning.
• volcengine — Alternative Chinese-language voices including specialty voices (e.g. film narration).
• edge — Microsoft Edge TTS voices including regional dialect options (e.g. Liaoning dialect). Supports rate and pitch.

Choosing a Voice and Emotion

Before generating speech, query the available voices for a provider:

curl https://tts.102465.xyz/api/voices?provider=azure

This returns a JSON list of voices and, for Azure, their supported emotions/styles. Use the voice's Chinese label (e.g. 晓晓) or English ID in the voice parameter, and pick an emotion from the voice's supported list for the emotion parameter.

Workflow

1. Clarify requirements — Ask the user what text they want spoken, in what language, and whether they have a preference for voice gender, style, or emotion.
2. Pick a provider — Default to azure unless the user needs a specialty voice from another provider. If unsure, query /api/providers and /api/voices?provider=<name> to browse options.
3. Generate the audio — Call /api/tts with the chosen parameters. For programmatic use, POST with JSON body; for a quick shareable link, construct a GET URL.
4. Deliver the result — If using curl/POST, save the MP3 to /mnt/user-data/outputs/ and present it to the user. If constructing a GET link, provide the URL so the user can play it in-browser.

Example GET URLs

Azure with emotion:

https://tts.102465.xyz/api/tts?text=今天天气真不错&provider=azure&voice=晓晓&emotion=温柔

Volcengine specialty voice:

https://tts.102465.xyz/api/tts?text=在遥远的东方，有一个古老的传说&provider=volcengine&voice=影视男解说%20中英混

Edge dialect voice:

https://tts.102465.xyz/api/tts?text=今天咱们唠唠嗑&provider=edge&voice=晓北%20辽宁%20女

Tips

• URL-encode Chinese characters and spaces when constructing GET URLs (e.g. %20 for space).
• The emotion parameter only works with Azure. Other providers ignore it.
• rate and pitch are percentages — positive values speed up / raise pitch, negative values slow down / lower pitch. They work with Azure and Edge.
• If the user doesn't specify a voice, omit the voice parameter to use the provider's default.
• When generating audio files programmatically, save as .mp3.