skills.rest
Tencent-RTC
Tencent-RTCOFFICIAL
Explore all skills by this author →
WebsiteGitHub

tts-clone

Clone a personalized voice from WAV samples for FlowTTS synthesis.

12|3|Updated Dec 11, 2025
Search Tags:#tts#voice-cloning#wav#voice-clone#voice-id#audio-sample#flowtts
One-click install
npx skills add https://github.com/Tencent-RTC/FlowTTS --skill tts-clone
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tts-clone
Source: https://github.com/Tencent-RTC/FlowTTS/tree/main/.claude/skills/tts-clone
Command: npx skills add https://github.com/Tencent-RTC/FlowTTS --skill tts-clone

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables developers to create a personalized voice clone from audio samples using FlowTTS, removing the guesswork from branding a unique voice for TTS deployments.

Core Features & Use Cases

  • Voice cloning from WAV samples: Create a distinct voice using 16kHz mono WAV samples and small prompts.
  • Environment validation: Check for Python 3.8+ and required credentials in .env.
  • End-to-end cloning workflow: Import sample, invoke Tencent Cloud TRTC, and obtain a VoiceId for synthesis.
  • Use Case: Brand a custom voice for customer support avatars or branded assistants.

Quick Start

Provide a WAV audio sample path and run the built-in example_voice_clone workflow to obtain a VoiceId for later synthesis.

Frequently Asked Questions about tts-clone

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

FAQPage Schema
How do I clone a voice from a WAV sample for TTS?▼

To clone a voice, provide a 16kHz mono WAV audio sample to invoke cloud-based cloning via Tencent Cloud TRTC, which processes the audio and outputs a VoiceId for subsequent TTS synthesis.

What are the requirements for voice cloning audio samples?▼

Voice cloning audio samples must be 16kHz mono WAV files between 10 and 180 seconds long. Validating these sample constraints ensures the cloud API can accurately process and generate the voice profile.

Do I need Python to create a custom voice clone?▼

Yes, creating a custom voice clone requires Python 3.8 or higher. You must also configure required credentials in a .env file to authenticate API requests with Tencent Cloud TRTC.

How does voice cloning work with FlowTTS?▼

Voice cloning with FlowTTS works by importing a WAV sample, invoking the Tencent Cloud TRTC API to create a personalized voice profile, and obtaining a unique VoiceId to use in FlowTTS synthesis tasks.

Can I brand a custom voice for customer support avatars?▼

Yes, you can brand a custom voice for customer support avatars by creating a distinct voice clone from WAV samples, generating a VoiceId that can be deployed for consistent TTS synthesis.

What is the best way to validate environment setup for voice cloning?▼

The best way to validate environment setup for voice cloning is checking for Python 3.8+ and confirming required Tencent Cloud TRTC credentials are configured in your .env file before importing samples.

Related Skills

Explore More Software Engineering Skills→
Tencent-RTCTencent-RTC
11

ai-custom-service-skill

Build a voice AI customer service agent using TRTC Conversational AI.

Official
Intermediate
mattmirelesmattmireles
57

audio-judge

Assess text-to-speech audio quality for intelligibility and acceptability.

Community
Intermediate
mxzinkemxzinke
2

stt

Transcribe audio recordings to text via a Whisper-compatible STT backend.

Community
Intermediate
Zedit42Zedit42

voice-cloning

Generate local speech audio and cloned voices as WAV files.

Community
Intermediate