skills.rest
augustscl
augustsclCOMMUNITY
Explore all skills by this author →
GitHub

tts

Convert text to spoken audio via MP3 streaming or JSON audioUrl output.

2|Updated Apr 6, 2026
Search Tags:#text-to-speech#tts#voiceover#audio-generation#listenhub#speaker-selection
One-click install
npx skills add https://github.com/augustscl/awesome-xiawang-skills --skill tts-augustscl
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tts
Source: https://github.com/augustscl/awesome-xiawang-skills/tree/main/tts
Command: npx skills add https://github.com/augustscl/awesome-xiawang-skills --skill tts-augustscl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Convert written text and scripts into natural-sounding spoken audio so users can listen to content instead of reading, enabling accessibility, voiceovers, and rapid content consumption.

Core Features & Use Cases

  • Quick single-voice TTS for instant, low-latency MP3 streams useful for chat replies, notifications, and short reads.
  • Scripted multi-speaker generation to produce dialogues, audiobooks, and multi-character voiceovers with per-segment speaker assignment.
  • Configurable output modes and persistence including inline playback, local download, and saving default speaker preferences per language.
  • Robust speaker selection and safety patterns: always fetch available speakers, respect API key presence, and follow interactive AskUserQuestion flows for enumerable choices.

Quick Start

Ask the skill to "朗读这段：" or "TTS this: The server will be down for maintenance at midnight."

Frequently Asked Questions about tts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert text to natural-sounding speech for immediate playback or download?▼

Converting text to natural-sounding speech is done by submitting written content to generate spoken audio for immediate playback or download. It supports single-voice quick reads and multi-speaker scripted dialogues.

Can I generate multi-speaker dialogues and audiobook voiceovers from a script?▼

Yes, you can generate multi-speaker dialogues, audiobooks, and podcast segments from scripts. The script mode uses per-segment speaker assignment and returns a JSON audioUrl along with subtitles for the generated audio.

Do I need a LISTENHUB_API_KEY to use the text-to-speech audio generation features?▼

Yes, text-to-speech audio generation requires a LISTENHUB_API_KEY for authentication. The system checks for API key presence and fetches available speakers via the speakers API before generating audio.

What's the difference between quick mode and script mode for voiceover generation?▼

Quick mode provides synchronous MP3 streaming for low-latency, single-voice short reads, while script mode produces multi-speaker audio by returning a JSON audioUrl and subtitles. Both modes support configurable output persistence.

How do I select and configure different speakers for text-to-speech conversion?▼

Speaker selection for text-to-speech conversion uses an interactive AskUserQuestion flow to choose from available speakers fetched via the API. You can also save default speaker preferences per language for future use.

Related Skills

Explore More Content & Communication Skills→
refly-airefly-ai
199

fal-audio-podcast

Generate multi-speaker podcast audio from dialogue scripts using Fal.ai VibeVoice 7B.

Official
Intermediate
GeneralReasoningGeneralReasoning
4

gtts

Convert text to speech with gTTS and generate MP3 audio files.

Official
Intermediate
ToqsickToqsick

audiobook

Convert text into audiobooks with multi-character voiceover and dialogue segmentation.

Community
Advanced
QvvvvvvQQvvvvvvQ
25

TTS

Convert text into speech audio using the z-ai-web-dev-sdk.

Community
Intermediate