Skip to main content

Audio & Video Tools

AI text-to-speech, speech recognition, plus video compression, trimming, voiceover, and more.

AI Text-to-Speech

Have AI read text aloud in a natural voice — perfect for product video voiceovers and audio introductions. Over 50 voices available, with automatic language detection for Chinese, English, Japanese, Korean, and more.

Basic Voiceover

Read this aloud: "Welcome to our store, featuring the latest wireless headphones"
Read this in Chinese: "欢迎来到我们的店铺"

Choose a Voice

Read this introduction using the Cherry voice
Generate this English narration with the Ethan voice
Not sure which voice to pick? Just say “add a voiceover” and AI will automatically choose an appropriate voice based on the content.

E-commerce Applications

Add a Chinese voiceover to this product video
Generate a 30-second product introduction audio
Read this product description in Japanese

Supported Languages

LanguageNotes
ChineseAuto-detected Mandarin
EnglishNatural American/British pronunciation
JapaneseNatural Japanese pronunciation
KoreanNatural Korean pronunciation
French, German, etc.Multi-language support

AI Speech Recognition

Convert speech in audio or video files to text. Supports multiple audio formats.

Basic Recognition

Transcribe this recording
[Upload audio file]
What does this video say
[Upload video file]

Specify Language

Transcribe this Chinese audio
[Upload audio]
Convert this English recording to text
[Upload audio]

E-commerce Applications

Transcribe the competitor's product video — I want to see how they pitch it
Convert customer voice feedback to text

Supported Formats

FormatNotes
MP3Most common audio format
WAVLossless audio
M4ADefault iPhone recording format
OGG / WebMWeb audio formats
Audio file size limit is 25MB. For longer recordings, trim first before transcribing.

Video Compression

Compress Video

Compress this video
[Upload video]
Compress video to under 10MB

Compression Guidelines

  • Social media: 1080p, 5-10MB
  • Product display: 720p, 2-5MB
  • Thumbnail preview: 480p, under 2MB

Video Trimming

Extract Segment

Extract video from 0:10 to 0:30
Trim first 15 seconds of video

Remove Intro/Outro

Remove last 5 seconds of video

Video Compositing

Add Background Music

Add background music to video
[Upload video] [Upload audio]

Add Voiceover

Add this voiceover to the video

Replace Audio

Replace the video's original audio
When adding audio, if audio is shorter than video it will loop, if longer it will be trimmed.

Video Concatenation

Merge Multiple Videos

Concatenate these videos
[Upload video1] [Upload video2] [Upload video3]

Set Order

Concatenate in order: Video A, Video B, Video C

Format Conversion

Convert Format

Convert video to MP4 format

Common Formats

FormatUse Case
MP4Universal format, best compatibility
WebMWeb playback
MOVHigh-quality editing

Generate Thumbnail

Extract Thumbnail

Extract a thumbnail from the video
Use frame at 5 seconds as thumbnail

Auto-Select

Automatically select best thumbnail
AI analyzes the video to select the clearest, most attractive frame as thumbnail.

Video Adjustments

Resize

Crop video to 1:1 square
Resize video to 9:16 vertical

Quality Enhancement

Enhance video clarity

Batch Processing

Batch Compress

Batch compress these videos

Batch Convert

Convert all videos to MP4
Batch processing may take longer. You’ll be notified when complete.

E-commerce Video Tips

Upload platforms usually have size limits. Keep under 50MB.
First 3 seconds are crucial. Grab attention immediately.
Many users watch with sound off. Subtitles improve message delivery.
Different platforms have different size requirements. May need multiple versions.