EmotiVoice provides a multi-voice text-to-speech engine with prompt controls.
Open source
24 alternativesBark
Generate audio from text prompts with Bark, a model for text-prompted audio creation.
About Bark
Bark is an open-source, transformer-based generative audio model from Suno, distributed as a GitHub repository. It creates audio from text prompts: speech, music, background noise, simple sound effects, and nonverbal sounds such as laughing, sighing and crying. It detects language automatically from the input text, and pretrained checkpoints are supplied ready for inference. The repository states the model is licensed under MIT and available for commercial use, while also noting it was developed for research purposes.
Bark is a fully generative model rather than a conventional text-to-speech system, so output can deviate in unexpected ways from the prompt, and Suno states it takes no responsibility for generated output. English quality is described as best for now, with other languages expected to improve. Bark supports over 100 speaker presets but does not currently support custom voice cloning. It can run on CPU or GPU, including GPUs with less than 4GB of VRAM. Pricing information is not provided in the source.
Key features
- Generates speech, music, background noise and simple sound effects from text
- Automatically detects language from the input text
- Supports multilingual output with code-switched text and native accents
- Offers 100+ speaker presets across supported languages
- Produces nonverbal sounds like laughing, sighing and crying
- Runs on CPU or GPU, including GPUs with under 4GB VRAM
Best for: Researchers and developers who want to run a text-prompted audio generation model and use its output under a permissive license.
Good for
- Released under the MIT License and stated as available for commercial use
- Pretrained model checkpoints are provided ready for inference
- Handles speech, music, sound effects and nonverbal sounds in one model
Watch out for
- Fully generative rather than conventional TTS, so output can deviate from the prompt
- Custom voice cloning is not currently supported
- English quality is best for now, with other languages expected to improve
Bark at a glance
- Website
- github.com/suno-ai/bark
- Category
- AI & Machine Learning › AI Voice & Audio
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Bark alternatives
Tools and sites you could use instead, ranked by how closely they match.
Kokoro provides an inference library for its open-weight 82-million-parameter text-to-speech model.
Open source
22 alternatives
The KittenTTS project offers a text-to-speech model described as under 25 MB in size.
Open source
24 alternatives
The whisper.cpp project ports OpenAI’s Whisper speech recognition model to C and C++.
Open source
24 alternatives
RVC WebUI is a framework for training voice conversion models with short voice recordings.
Open source
24 alternatives
Applio provides free open source voice conversion, custom voice model training, and real time conversion.
Open source
24 alternativesPopular in AI Voice & Audio
Well-known listings from the same topic.
Google Illuminateilluminate.google.comAlteredaltered.aiELSA Speakelsaspeak.comKreadoAIkreadoai.comPodwisepodwise.aiAddsubtitleaddsubtitle.ai
Bark FAQ
Can Bark output be used commercially?
Yes. The repository states Bark is licensed under the MIT License, which makes it available for commercial use.
Does Bark support custom voice cloning?
No. Bark matches the tone, pitch, emotion and prosody of a given preset, but the repository says custom voice cloning is not currently supported.
Can Bark run on GPUs with limited VRAM?
Yes. The repository states Bark can be used with GPUs that have less than 4GB of VRAM.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.