Kitten-TTS
Open-source text-to-speech models with voice cloning that run in real time on a CPU, with no GPU needed.
AI Audio & VoiceFreeverified Listed on Open source
Is Kitten-TTS free?
Yes, Kitten-TTS has a free plan. What you get: Run the models yourself; hosted API has 30 free minutes. To get it: install with pip install kittenml; then load a model and generate speech with a built-in voice or a reference clip; then save the audio to a file. Verified on github.com.
Free plan at a glance
- Includes
- Run the models yourself; hosted API has 30 free minutes
Open source: the models run on your own machine with no usage limit stated. KittenML's hosted API gives 30 free minutes, then pay as you go.
- Duration
- Free forever
- Commercial use
- Allowed on the free plan
How to get it free
Self-host- Install with pip install kittenml
- Load a model and generate speech with a built-in voice or a reference clip
- Save the audio to a file
Good to know
- Free commercial use of the Kitten-TTS 2 weights only under $1M revenue and funding, with registration
- Using the model or its audio to train another model isn't allowed
github.com, Checked Source
Overview
Kitten-TTS is a family of open-source text-to-speech models from KittenML. The flagship model, Kitten-TTS 2, clones a voice from 5-30 seconds of audio and takes emotion tags, and lighter models run on a CPU without a GPU.
Free vs paid
| Free | Pro | |
|---|---|---|
| Price | $0 | $24.99/mo |
| Includes |
| Plan details |
Key features
- Voice cloning from 5-30 seconds of a single speaker, with no fine-tuning
- Emotion tags, inline sound events such as <laugh> and emphasis markup (in beta)
- Lightweight 15M-80M parameter models that run on a CPU without a GPU
- Fast CPU inference through a llama.cpp fork, MLX on Apple silicon and vLLM on NVIDIA GPUs
- Long-text chunking and streaming, with 24 kHz audio output
- Docker image that serves an OpenAI-compatible speech API
Best for
- People
- Developers adding speech or voice cloning to apps, Builders of voice features for devices without a GPU, Small companies that want a speech model they can host themselves
Limitations
- Free commercial use of the Kitten-TTS 2 weights only for companies under $1M in revenue and funding, after registering
- Commercial users must credit "Powered by KittenML", and the license bans training other models on it
- Emotion control is in beta and steers delivery rather than guaranteeing it
Screenshot
FAQ
- Is Kitten-TTS free?
- Yes. Kitten-TTS has a free plan: Run the models yourself; hosted API has 30 free minutes. We last checked github.com's pricing page on 2026-10-24.
- What does the Kitten-TTS free plan include?
- Run the models yourself; hosted API has 30 free minutes. Source: https://github.com/KittenML/KittenTTS (checked 2026-10-24).
- How do I get Kitten-TTS for free?
- Steps: Install with pip install kittenml; Load a model and generate speech with a built-in voice or a reference clip; Save the audio to a file. Start at https://github.com/KittenML/KittenTTS (checked 2026-10-24).
- Do I need an account to use Kitten-TTS for free?
- Not for the free option: the free route is to self-host Kitten-TTS (Install with pip install kittenml). Checked 2026-10-24.
- What's the catch with Kitten-TTS's free plan?
- Free commercial use of the Kitten-TTS 2 weights only under $1M revenue and funding, with registration. Using the model or its audio to train another model isn't allowed. Checked 2026-10-24.
- How much does Kitten-TTS cost after the free plan?
- The cheapest paid plan is the Pro plan, at $24.99 a month, billed monthly. We checked kittenml.com's pricing page on 2026-10-24.Source: kittenml.com
- What are free alternatives to Kitten-TTS?
- NaturalReader, Fish Audio and TTSMaker all have free plans. We checked their free offers on 2026-10-25.
- Does Kitten-TTS need a GPU?
- No. The README says Kitten-TTS 2 runs in real time on CPUs and consumer GPUs, and the lightweight 15M-80M models run on a CPU without a GPU.Source: github.com/KittenML/KittenTTS
- Is there a hosted version?
- Yes. KittenML's hosted API has a free tier of 30 free minutes of speech and transcription, then pay as you go, and KittenML says or subscription is needed. Pro costs $24.99 a month on monthly billing.Source: kittenml.com
Free alternatives
NaturalReader
Text-to-speech reader for documents and web pages.
Free forever, Free voices with daily limits
Fish Audio
Text-to-speech and voice cloning.
Free forever, Limited monthly generations
TTSMaker
Free online text-to-speech tool with many voices.
Free forever, Free text-to-speech with weekly character limits
Transkriptor
AI transcription.
Free forever, 'Free - 90 Minutes' of transcription (paid plans from Lite $9.99/month)
Luvvoice
Free unlimited AI text-to-speech.
Free forever, 10,000 characters a month, 3,000 per conversion
Compare
- Kitten-TTS vs ElevenLabs · free plans side by side
Sources
- Free offer
- Verified on github.com/KittenML/KittenTTS
…is a series of sota open-source text-to-speech models, built by…
Added by our team. We check that a free option exists and record the date; signing up is between you and Kitten-TTS, so read their privacy policy and terms first.
Is this your tool? Claim it · Promote it
