coze-voice-gen

Generate speech from text and transcribe audio using the coze-coding-dev-sdk.

Updated Feb 15, 2026

Search Tags:#speech recognition #audio processing #tts #voice generation #coze #asr

Ready to run

npx skills add https://github.com/sksdwl/shudan --skill coze-voice-gen

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: coze-voice-gen
Source: https://github.com/sksdwl/shudan/tree/main/workspace/skills/coze-voice-gen
Command: npx skills add https://github.com/sksdwl/shudan --skill coze-voice-gen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires coze-coding-dev-sdk, ts-node, and includes scripts (resource) components.

What problem does it solve?

This Skill streamlines audio content creation and processing by providing advanced Text-to-Speech (TTS) and Speech-to-Text (ASR) capabilities.

Core Features & Use Cases

Text-to-Speech (TTS): Convert written text into natural-sounding speech with various voice options, speaking rates, and audio formats.
Speech-to-Text (ASR): Transcribe spoken audio from URLs or local files into written text, including duration and segment information.
Use Case: Generate voiceovers for marketing videos, create audio versions of articles, or transcribe customer service calls for analysis.

Quick Start

Use the coze-voice-gen skill to convert the text "Hello, this is a test." into speech using the default voice.

Frequently Asked Questions about coze-voice-gen

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

FAQPage Schema

How do I convert text to speech using coze-coding-dev-sdk?▼

To convert text to speech, this Skill uses the coze-coding-dev-sdk to generate natural-sounding speech from written text. You can customize voice options, speaking rates, and audio formats to suit your specific audio content creation needs.

Can I transcribe audio files to text and get segment analysis?▼

Yes, you can transcribe audio files or URLs to text using the Speech-to-Text ASR functionality. It provides written text output that includes detailed duration and segment information for comprehensive audio processing and analysis.

Does this voice generation tool support customizable speaking rates?▼

Yes, the Text-to-Speech functionality supports customizable voice options, speaking rates, and audio formats. This allows you to adjust the generated speech output to match the specific pacing and style required for your voiceover or audio content.

What's the best way to transcribe customer service calls for analysis?▼

The best way to transcribe customer service calls is using the Speech-to-Text ASR feature. It transcribes spoken audio from URLs or local files into written text, providing duration and segment information for detailed analysis of the conversation.

Do I need npx and ts-node to run text-to-speech scripts?▼

Yes, you need npx and ts-node because this Skill integrates with npx for script execution and lists ts-node as a dependency. These tools are required to run the scripts that execute the text-to-speech and speech-to-text processing.

Can I use local audio files for speech-to-text transcription?▼

Yes, the Speech-to-Text ASR capability supports transcribing spoken audio from local files or URLs. This allows you to easily process existing audio recordings and convert them into written text with duration and segment analysis.