F5-TTS （Asynchronous Text-to-Speech）

POST

/302/submit/f5-tts-sync

302.AI's API comes from models we deployed on cloud GPUs. Some models are open-source, while others are fine-tuned or developed by 302.AI.
Open source voice cloning，From: https://github.com/SWivid/F5-TTS?tab=readme-ov-file
Average runtime 10-20s

Price：50 PTC/1M characters

Request

Header Params

Authorization

string

required

Example:

Bearer {{YOUR_API_KEY}}

Body Params application/json

gen_text

string

required

Text for Speech Generation

ref_audio_url

integer

required

Clone voice file URL, at least 15 seconds

ref_text

string

optional

Clone the content of the voice file

model_type

string

required

F5_TTS

Example

{
  "gen_text": "三零二AI是一个汇集全球顶级品牌的AI超市，汇集全球各类顶尖AI模型，提供多种AI机器人，各种AI工具的使用和AI API接入。",
  "ref_audio_url": "https://raw.githubusercontent.com/SWivid/F5-TTS/refs/heads/main/src/f5_tts/infer/examples/basic/basic_ref_zh.wav",
  "model_type": "F5-TTS"
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/302/submit/f5-tts-sync' \
--header 'Authorization: Bearer sk-jls4AaVBGoe1GwZD64qZA1qyKTN1MPHa4NmvH1cT68z7K1Zz' \
--header 'Content-Type: application/json' \
--data-raw '{
  "gen_text": "三零二AI是一个汇集全球顶级品牌的AI超市，汇集全球各类顶尖AI模型，提供多种AI机器人，各种AI工具的使用和AI API接入。",
  "ref_audio_url": "https://raw.githubusercontent.com/SWivid/F5-TTS/refs/heads/main/src/f5_tts/infer/examples/basic/basic_ref_zh.wav",
  "model_type": "F5-TTS"
}'

Responses

🟢200OK

application/json

Body

completed_at

string

required

created_at

string

required

error

string

required

string

required

model

string

required

output

string

required

started_at

string

required

status

string

required

Example

{
    "completed_at": "",
    "created_at": "",
    "error": "",
    "id": "",
    "model": "",
    "output": "",
    "started_at": "",
    "status": ""
}

Modified at 2024-12-13 02:58:28

F5-TTS（Text to Speech）

F5-TTS （Asynchronously Retrieve Results）