Function Introduction

Input a piece of voice, and generate a voice translated into another language based on the timbre of the original voice.

Processing Flow Description

🔄 Overall Processing Flow

Input Audio → Speech Recognition (STT) → Text Translation → Voice Cloning → Text-to-Speech (TTS) → Output Audio

The system will automatically complete end-to-end translation from audio to audio, maintaining the original or specified timbre characteristics.

Details of Processing Steps

📋 Five Core Steps

1️⃣ Initialization (`initialization`)

Download and prepare the audio file

Automatically crop the cloned audio to within 30 seconds

2️⃣ Speech Recognition (`speech_to_text`)

Convert audio to text using OpenAI gpt-4o-transcribe

3️⃣ Translation (`translation`)

Users can choose their own LLM model (by default, the claude-haiku-4-5-20251001 model is used) for intelligent translation.

4️⃣ Voice Cloning (`voice_clone`)

Analyze and extract audio features

5️⃣ Text-to-Speech (`text_to_speech`)

Generate target language audio using the cloned timbre

Output high-quality audio files

Supplier Selection Logic

🎯 Automatic Selection Rules

The system will automatically select the best voice cloning supplier based on the target language:

供应商	支持语言	自动选择条件
Fish	All languages	Default use in non-Chinese and non-English scenarios
index_tts2	Chinese, English	Priority is given to Chinese-English mutual translation
soulx	Chinese, English	Used when specified manually by the user
f5	Chinese, English	Used when specified manually by the user
voxcpm	Chinese, English	Used when specified manually by the user

Selection Priority

User Designation: If a supplier is specified and supports the target language, it will be used first.

Language Matching: For Chinese and English, index_tts2 is preferred; for other languages, Fish is used.

⚠️ Notes

It is recommended that the duration of the cloned audio be 10-30 seconds; excessively long audio will be automatically clipped.

The audio must be clear and free of noise to achieve the best results.

Supported formats: mp3, wav

Request

Header Params

Body Params application/jsonRequired

Example

{
  "audio_file_url": "https://file.302ai.cn/gpt/imgs/20251113/8c68d17098dde0e2dd8bb3e8407a898b.mp3",
  "clone_audio_file_url": "",
  "target_language": "zh",
  "source_language": "",
  "voice_clone_provider": "fish"
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

application/json

Body

Example

{
    "task_id": "25691459-2665-41e1-86fe-2d37d48a95c1",
    "status": "pending",
    "message": "任务已创建并开始处理"
}

Create an audio translation task

Function Introduction

Processing Flow Description

🔄 Overall Processing Flow

Details of Processing Steps

📋 Five Core Steps

1️⃣ Initialization (`initialization`)

2️⃣ Speech Recognition (`speech_to_text`)

3️⃣ Translation (`translation`)

4️⃣ Voice Cloning (`voice_clone`)

5️⃣ Text-to-Speech (`text_to_speech`)

Supplier Selection Logic

🎯 Automatic Selection Rules

Selection Priority

⚠️ Notes

Request

Request Code Samples

Responses

Create an audio translation task

Function Introduction#

Processing Flow Description#

🔄 Overall Processing Flow#

Details of Processing Steps#

📋 Five Core Steps#

1️⃣ Initialization (initialization)#

2️⃣ Speech Recognition (speech_to_text)#

3️⃣ Translation (translation)#

4️⃣ Voice Cloning (voice_clone)#

5️⃣ Text-to-Speech (text_to_speech)#

Supplier Selection Logic#

🎯 Automatic Selection Rules#

Selection Priority#

⚠️ Notes#

Request

Request Code Samples

Responses

Function Introduction

Processing Flow Description

🔄 Overall Processing Flow

Details of Processing Steps

📋 Five Core Steps

1️⃣ Initialization (`initialization`)

2️⃣ Speech Recognition (`speech_to_text`)

3️⃣ Translation (`translation`)

4️⃣ Voice Cloning (`voice_clone`)

5️⃣ Text-to-Speech (`text_to_speech`)

Supplier Selection Logic

🎯 Automatic Selection Rules

Selection Priority

⚠️ Notes