| What it does | Production-ready text-to-speech with precise duration control and emotional expression
| Auto captions for TikTok, Reels, and Shorts
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: $0/month with 20,000 characters per month and 3 custom voices. Pro: $14.99/month with 1,000,000 characters per month and 20 custom voices.
| Free: $0 forever, 5 videos per month up to 3 min each. Starter: $6/month, 15 videos per month up to 5 min each. Pro: $12/month, 30 videos per month up to 10 min each. Business: $36/month, 100 videos per month up to 10 min each. All paid plans billed monthly with no commitment and cancel anytime.
|
|---|
| Key features | - Precise timing control with exact token specifications
- Rich emotional range including joy, tranquility, anger, and anxiety
- Voice-emotion separation for independent control
- Natural language emotion shaping powered by Qwen3
- Eight-dimensional emotion vectors (happy, angry, sad, afraid, disgusted, melancholic, surprised, calm)
- Custom voice uploads and recordings (up to 20 on Pro plan)
- Commercial use rights on Pro plan
- Support for English and Chinese languages
- MP3 and WAV audio format output
- Priority processing for Pro users
| - Automatic transcription with punctuation and speaker detection
- AI word-by-word caption styling with emphasis and emojis
- Scene grouping and automatic look assignment
- Multi-speaker detection with per-speaker styling
- Customizable templates for TikTok, Reels, and Shorts
- Full transcript editing: rewrite words, retime scenes, split lines
- Captions burned into video frames for universal playback
- Support for 93 languages including English, Spanish, Portuguese, French, German, Italian, Dutch, Russian, Japanese, Mandarin, and more
- Browser-based export at any resolution including 4K
- Local version: privacy-first, in-browser, no uploads or accounts
|
|---|
| What makes it different | Not given
| - Animated captions with word-by-word reveal and per-word emphasis, which cannot be expressed in subtitle formats
- Captions built into the video play identically on TikTok, Reels, Shorts and everywhere else, unlike subtitle tracks which these platforms ignore
- AI automatically picks the words that matter and gives them emphasis for each scene
- Free tier requires no account, no card, and allows full editing and export before signup
- Fully customizable templates with raw CSS editing and SVG filter support for pixel-perfect control
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 14 ▲ +1 (up) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 8 | 1 |
|---|
| Citation Flow (Majestic) | 18 | 19 |
|---|
| Referring domains (Majestic) | 12 | 10 |
|---|
IndexTTS2
tscaps