api-tts

Convert text to speech via Volcengine TTS with configurable voices and formats.

27|9|Updated Jan 25, 2026

Search Tags:#voice #text-to-speech #synthesis #audio #tts #volcengine #multivoice

Ready to run

npx skills add https://github.com/Leoyishou/personal-ai-company --skill api-tts

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: api-tts
Source: https://github.com/Leoyishou/personal-ai-company/tree/main/claude-global/skills/api-tts
Command: npx skills add https://github.com/Leoyishou/personal-ai-company --skill api-tts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

This skill enables converting text into natural-sounding speech using Volcengine TTS, allowing users to generate audio assets without manual voice recording.

Core Features & Use Cases

Voice variety: choose from multiple voices and adjust speed and encoding to suit different contexts.
Flexible outputs: supports MP3/WAV/PCM/OGG_OPUS and various sample rates for easy integration into videos, apps, or accessibility tools.
Use Case: create podcast intros or narration for videos by converting scripts into ready-to-use audio files.

Quick Start

Provide the text you want to synthesize and run the tool to generate an audio file.

Frequently Asked Questions about api-tts

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

FAQPage Schema

How do I convert text to speech for video narration and podcasts?▼

Converting text to speech is done here using Volcengine TTS to generate natural-sounding audio files from scripts. You provide the text, select a voice, adjust speed, and receive an output file path ready for video narration or podcast integration.

What audio formats and sample rates does Volcengine text-to-speech support?▼

Volcengine text-to-speech supports MP3, WAV, PCM, and OGG_OPUS audio formats with various configurable sample rates. This flexibility ensures the generated speech output integrates easily into diverse applications, accessibility tools, and multimedia projects.

Do I need an API token to generate speech from text?▼

Generating speech from text requires the VOLC_TTS_APPID and VOLC_TTS_TOKEN credentials to authenticate with the Volcengine TTS service. These values can be configured in your environment or passed directly via the command line when running the tool.

Can I use multiple voices and adjust the speed for text-to-speech synthesis?▼

Text-to-speech synthesis supports multiple configurable voices and adjustable speed settings. This allows you to tailor the generated audio assets to suit different contexts, from fast-paced podcast intros to slower, clear accessibility narration.

What's the best way to generate audio assets without manual voice recording?▼

The best way to generate audio assets without manual voice recording is using automated text-to-speech synthesis. This skill converts your written scripts into ready-to-use audio files, eliminating the need for microphones or studio time while maintaining natural-sounding output.