Text to Speech AI Agents Music Audio to Text Voice Cloning Voice Design Marketplace More
Report Bug / Feature Request
Kani TTS 2

Default

Standard English Neutral Kani TTS 2

Default is a neutral AI voice powered by the Kani TTS 2 text-to-speech model. This free-tier voice speaks English and delivers high-quality speech synthesis. With near-instant generation speed and a quality rating of 4/5, Default is well-suited for fast english generation on low-vram hardware, quick previews. The Kani TTS 2 engine is developed by NineNineSix under the Apache 2.0 license, making it safe for commercial use. Key capabilities include: 3gb vram, ultra-fast, lightweight, nanocodec, free.

No ratings yet
Try This Voice All Kani TTS 2 Voices

Kani TTS 2Model Information

Model Kani TTS 2
Developer NineNineSix
Quality
Speed Fast
License Apache 2.0
Cloning Not available
Tier Standard (2x characters)
Parameters 400M
Architecture LFM2 + NanoCodec
Training Data 10000 hours
Year 2026

Best Use Cases for Default

Recommended applications based on this voice's characteristics

Audiobooks & Narration

Use Default to narrate long-form content with natural prosody and expression.

Video Voiceovers

Add professional narration to YouTube videos, ads, and social media content.

Apps & Accessibility

Fast generation makes this voice ideal for real-time apps, screen readers, and accessibility tools.

E-Learning & Training

Create engaging training materials, courses, and educational content with clear AI narration.

Frequently Asked Questions

Kani-TTS-2 by NineNineSix is an ultra-lightweight 400M parameter model built on a Liquid AI LFM2 backbone with NVIDIA NanoCodec. It runs in just 3GB VRAM and produces ~10 seconds of speech in ~2 seconds on an A100 (RTF 0.2). The current public release ships an English-only `kani-tts-2-en` checkpoint and does not expose the speaker-embedding hook needed for voice cloning — use Chatterbox / IndexTTS2 / F5-TTS for cloning, or Kokoro / MeloTTS for non-English.

Kani TTS 2 was developed by NineNineSix and is released under the Apache 2.0 license, which permits commercial use of generated audio.

Kani TTS 2 supports 1 language: English.

Kani TTS 2 is in the Free tier — free — no credits required. You can preview any Kani TTS 2 voice for free before generating full audio.

Kani TTS 2 has very fast generation speed. It runs in near real-time, making it suitable for streaming and interactive applications.

Kani TTS 2 is rated 4/5 for audio quality on TTS.ai. It produces high-quality, natural-sounding speech.

No, Kani TTS 2 uses a fixed set of built-in voices. For voice cloning, try models like CosyVoice 2, GPT-SoVITS, or Chatterbox.

Yes, Kani TTS 2 is specifically recommended for fast english generation on low-vram hardware, quick previews. Its 3gb vram, ultra-fast, lightweight capabilities make it an excellent choice for this use case.

Yes, Kani TTS 2 is licensed under Apache 2.0, which allows commercial use. Audio generated with Kani TTS 2 voices can be used in videos, podcasts, apps, games, and any other commercial project.

Yes, all voices on TTS.ai use commercially-licensed open-source models (MIT, Apache 2.0). The generated audio is yours to use in videos, podcasts, apps, games, and any other commercial application.

Send a POST request to /api/v1/tts/ with the model name and voice ID. See our API Documentation page for code examples in Python, JavaScript, Go, and cURL.

Yes, click the play button on this page to hear a sample. You can also type custom text on the Text to Speech page and generate a free preview with any voice.

Try Default Now

Type any text and hear it spoken by Default. Free to use.

Generate Speech Sign Up Free