Create Lifelike Audio

Start typing here to create lifelike audio in multiple languages, voices and emotions with Flow TTS.

TEXT TO SPEECH
Radiant Girl
AI

Audio Tools

Clone Your Voice

Experience instant voice magic with just 10 seconds of audio input!

Original Audio
▶
Cloned Result
▶

Voice Design

Create Any Voice You Can Imagine - From Simple Text Description

Pirate Captain
Greedy Goblin
Southern Belle

Explore voices to match your need

Explore more >
Dubbing
New
Instant Clone
Library
My Voices
Collected Voices
Voice slots remaining: 0/0
Try:

Voice Cloning

Clone a voice using as little as a 10-second clean voice clip.

Import your Voice

Add or drop a file
Up to 50MB each
or
Record audio
6-180 seconds long
This name will help you identify the cloned voice later
Please upload a clean voice recording in a quiet environment. Reverb, multiple speakers, background noise, etc., will affect the voice cloning quality.

Advanced Settings (Optional)

Remove Background Noise
Enable Accent Optimization

Text to Preview

151 / 1000 characters
Voice slots remaining: 0/0

Your Cloned Voices

Pick Your Subscription

Select the plan that suits you best, or easily top-up your credits.

Free

Limited-time
$0/month
Bonus 10000 credits (~12 mins audio), non-cumulative
Plan's Feature:
Generate speech in 40 languages in multiple accents using tons of unique voices!
Limited-time free: Generate speech with specified emotion & language
Clone up to 3 voices with as little as 10 seconds of audio

Starter

$5
$4/month
Billed yearly
100K credits per month (~2 hours of high-quality HD model)
Bonus 10000 credits (~12 mins audio), non-cumulative
Everything in Free, plus:
Faster speed of generating speech
Generate speech with specified emotion and language
Clone up to 10 voices with as little as 10 seconds of audio

Creator

$15
$12/month
Billed yearly
250K credits per month (~5 hours of high-quality HD model)
Bonus 10000 credits (~12 mins audio), non-cumulative
Everything in Free, plus:
Faster speed of generating speech
Generate speech with specified emotion and language
Clone up to 30 voices with as little as 10 seconds of audio
🌟 Most Popular

Standard

$30
$24/month
Billed yearly
600K credits per month (~12 hours of high-quality HD model)
Bonus 10000 credits (~12 mins audio), non-cumulative
Everything in Free, plus:
Faster speed of generating speech
Generate speech with specified emotion and language
Clone up to 50 voices with as little as 10 seconds of audio

Voice Isolator

Isolate background noise to get pure speech audio for better quality.

Upload or drop an audio file (WAV, MP3, M4A, FLAC), max 100MB / 5 minutes

Dubbing

Localize content across 29 languages with AI dubbing.

Learn

Learn about the Dubbing editor

A professional app for dubbing content.

Importing YouTube videos

Learn how to dub any YouTube video.

Recent Dubs
Name
Language
Created at
Saved
0 words
Voice Settings
1.0x
0
50
Voice Library

正在合成音频

合成中 0/0

请勿关闭页面，合成完成后将自动下载

Video Dubbing

Transform your videos with AI-powered voice dubbing. Upload, transcribe, and generate professional voiceovers in minutes.

1
Upload
2
Transcribe
3
Edit
4
Synthesize
5
Export
🎥

Upload Media File

Support MP4, WebM, MP3, WAV formats, up to 500MB

Or drag and drop file here

Developers

API Pricing ↗ Documentation ↗
Overview
API Keys
Webhooks
Usage

Developer quickstart

Learn the basics and make your first request with the Flow TTS API.

Get started
Python
1234567891011121314151617 
from tencentcloud.trtc.v20190722 import trtc_client, models

# Initialize client
client = trtc_client.TrtcClient(cred, "ap-beijing")

# Build request
req = models.TextToSpeechRequest()
req.from_json_string(json.dumps({
    "SdkAppId": 1400704311,
    "Model": "flow_01_turbo",
    "Text": "你好，世界",
    "Voice": {"VoiceId": "v-female-R2s4N9qJ"}
}))

# Call API
resp = client.TextToSpeech(req)
audio = base64.b64decode(resp.Audio)
Quick Links
Get SecretKey
Browse Models
API Reference
Libraries & SDKs
Usage & Billing
Pricing Overview

AI Podcast Generator

Generate professional podcasts with AI-powered script generation and multi-speaker synthesis.

Quick Start with Templates

Interview

Host + Guest dialogue format

2 speakers

Discussion

Two-person topic discussion

2 speakers

News Broadcast

Single anchor news style

1 speaker

Story Narration

Single narrator storytelling

1 speaker
Learn

AI Script Generation

Let AI generate professional podcast scripts for you.

Multi-Voice Synthesis

Assign unique voices to each speaker for natural conversations.

Recent Podcasts
Name
Duration
Created at

No podcasts yet

Create your first AI-powered podcast and start your content creation journey.

Voice Universe

Immerse yourself in the infinite universe of voice artistry. Explore masterpieces from creators worldwide, from inspiration to creation—every voice becomes a unique work of art.