Kokoro TTS
Free planLightweight, fast open-source TTS
A lightweight open-source speech synthesis model with 82 million parameters that delivers audio quality on par with much larger models despite its small size. It runs fast even on a CPU or a low-end GPU.
vs. similar tools: Its Apache 2.0 license allows unrestricted commercial use, and it can synthesize speech in real time with as little as 1-2GB of VRAM.
Overview
At a glance
- 82M params run real-time synthesis even on a CPU or low-end GPU
- Apache 2.0 license allows unrestricted commercial use
- Needs only 1-2GB VRAM, so it fits a personal machine
- No Korean support, unsuitable for Korean-language voice
- No hosted API, so you wire up serving and code yourself
- Best for: Developers and makers who want free, self-run English TTS
Read more
Kokoro TTS is a lightweight open-source speech synthesis model with 82 million parameters, used by pulling its public GitHub code and running it on your own server or personal machine. It suits developers who want to operate speech synthesis themselves without cloud bills, and solo makers who need to use the output freely.
Its biggest draw is efficiency relative to size. It can synthesize speech in real time with just 1-2GB of VRAM and runs fast even on a CPU with no GPU at all.
That said, it does not support Korean, so it is hard to apply directly to Korean-language content. No hosted API is provided, so you have to stand up the model and connect it to your service yourself, and there is no voice cloning. As a result, if you are not comfortable with code and infrastructure, the ease-of-use rating of 65 may feel even lower in practice.
In short, it is a recommendable pick for developers who want to synthesize English voice in their own environment without cost. Those who need Korean dubbing, or who want a ready-to-use API and voice cloning without writing code, are better off considering other tools alongside it.
Pricing
| Plan | Monthly price | Limits |
|---|---|---|
| Open source | $0/mo | Apache 2.0 license, free to self-host |
Specs
- Voice cloning
- Not supported
- Real-time
- Supported
- API
- No
- Open source
- Yes
- Self-hosting
- Available
- Korean support
- Not supported
- Commercial use
- Allowed
Popularity
Buzz and recognition on absolute thresholds
Absolute-threshold score
46
High confidence5/5 signals
Each axis maps to a 1-10 absolute threshold where 10 means broadly recognizable. Collected: 2026-06-13.
Related tools
By popularity
- ElevenLabs
Its expressive, multilingual voice quality and rich API and ecosystem have made it an industry standard.
- Otter.ai
It delivers realtime transcription and meeting summaries as a finished app, then extends into connected-app search and follow-up workflows.
- HeyGen
It leads in avatar presenter videos and multilingual dubbing quality.
- Fireflies.ai
With 100+ transcription languages, AskFred, CRM/work-app integrations, and APIs, it is built to turn meeting notes into automated workflows.
- AssemblyAI
It goes beyond transcription by packaging natural-language prompting, keyterm boosts, medical mode, and voice agent APIs in one platform.
Compare Kokoro TTS
Last updated: 2026-05-30
All tools