| What it does | Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
| AI vocal and music separator for creating acapellas, instrumentals, and karaoke tracks
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | SG
| Not given
|
|---|
| Pricing model | Open source
| Not given
|
|---|
| Pricing | Free to use. Free Chrome Extension with 10,000 characters free every month.
| Free tier: 30-second preview without sign-in, 1 minute free downloads after sign-in, 10 clips up to 30 seconds daily. Pro: $9.99/month for 20 hours monthly. Pay-as-you-go: 20 Minute Pack $1.99, 1 Hour Pack $4.99, 10 Hour Pack $14.99.
|
|---|
| Key features | - 82M parameter efficiency for lightweight, scalable performance
- Multilingual support including English, French, Korean, Japanese, and Mandarin
- Customizable voice packs with multiple lifelike voice options
- Automatic content segmentation for chapter and section detection
- OpenAI-compatible API endpoint for easy integration
- Real-time audio generation with NVIDIA GPU acceleration
- Processes up to 510 tokens in a single pass for longer audio outputs
- Chrome extension for reading webpages aloud
| - BS-RoFormer AI model for source separation with 18.10 dB instrumental SDR on MVSEP leaderboard
- Supports MP3, WAV, FLAC, AIFF, M4A, AAC, OGG, OPUS audio and MP4, MOV, M4V, WEBM, MKV video up to 2 GB
- Returns both tracks as 44.1 kHz, 16-bit WAV or MP3 with sample alignment
- Speed control from 50% to 150% without changing pitch
- Key shift up or down by up to 6 semitones without changing speed
- BPM and key detection on acapella extractor
- 24-bit WAV output option at 44.1 or 48 kHz on acapella extractor
- Remove background noise, hum, fans, traffic, and room echo from speech
|
|---|
| What makes it different | - Outperforms larger models like XTTS (467M params) and MetaVoice (1.2B params) despite having only 82M parameters
- Open-source and free for both commercial and personal use under Apache 2.0 license
- Lightweight architecture enabling deployment on CPU and GPU with minimal resources
- Trained on high-quality, permissively licensed audio for accurate natural-sounding speech
- Designed for scalability while preserving excellent audio quality
| - Uses AI source separation instead of phase cancellation, keeping bass and drums intact
- Automatic file deletion after 24 hours for privacy
- Fast processing on dedicated cloud GPUs with instant preview as upload begins
|
|---|
| 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) | 36 ● no change since last check | 5 ▲ +3 (up) since last check |
|---|
| Trust Flow (Majestic) | 10 | 0 |
|---|
| Citation Flow (Majestic) | 22 | 0 |
|---|
| Referring domains (Majestic) | 154 | 0 |
|---|
Kokoro TTS
Vocal Isolator