G
GetLLMs
Back to Models

F5-TTS Vietnamese Text-to-Speech

Discover F5-TTS Vietnamese Text-to-Speech, a powerful model from EraX-AI. It excels in zero-shot voice cloning and produces natural Vietnamese speech.

Platform: Replicate
Vietnamese TTSZero-Shot Voice CloningSpeech Synthesis
79 runs
T4
License Check Required

🚀Function Overview

A Vietnamese text-to-speech model that converts input text into speech using reference audio for voice cloning with adjustable speech parameters.

Key Features

  • Converts Vietnamese text to natural speech
  • Supports zero-shot voice cloning via reference audio
  • Adjustable speech speed control
  • Automatic text extraction from reference audio when needed

Use Cases

  • •Creating personalized voiceovers for Vietnamese content
  • •Developing voice assistants with custom voices
  • •Accessibility tools for text-to-audio conversion
  • •Generating speech samples for language learning

⚙️Input Parameters

input_text

string

Input text to convert to speech | Văn bản cần đọc

reference_audio

string

Reference audio file in wav format | Giọng tham chiếu, chỉ nhận file wav

reference_text

string

Reference text, must match the reference audio | Văn bản tham chiếu, phải trùng với giọng tham chiếu, nếu trống sẽ tự động trích xuất từ audio

speed

number

Speed of the speech | Tốc độ đọc

💡Usage Examples

Example 1

Input Parameters

{
  "speed": 1,
  "input_text": "Đây là đài tiếng nói Việt Nam. Phát thanh từ kênh trung ương Hà Nội.",
  "reference_text": "Càng trưởng thành bạn càng nhận ra tranh luận đúng sai, hơn thua cũng không còn quan trọng nữa.",
  "reference_audio": "https://replicate.delivery/pbxt/Mr9f6kUPs0oOP841x4pV4n0vSBafLSf4yEgSjYkOAqN57CUl/ash_vn.wav"
}

Output Results

https://replicate.delivery/czjl/OB8PX8kbeSXhHi0228AvrQjIKFooSTaViG8Xff5e9DzYihPSB/c4cded21-cf7f-458b-b357-48492f3671dd.wav

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type
T4
Run Count
79
Commercial Use
Unknown/Restricted
Platform
Replicate

Related Keywords

Zero-Shot Voice CloningVietnamese VoiceoversAdjustable Speech SpeedCustom Voice AssistantsText-to-Audio ConversionLanguage Learning Speech

Related Models

Chatterbox TTS

Chatterbox is a state-of-the-art zeroshot TTS

NVIDIA PDF to Podcast

Transform PDFs into AI podcasts for engaging on-the-go audio content.

Piper Persian Text-to-Speech

A fast, local neural text to speech system that sounds great and is optimized for the Raspberry Pi 4. Piper is used in a variety of projects.