ESPnet includes tools for end to end speech processing and related speech tasks.
Open source
24 alternativesEmotiVoice
EmotiVoice provides a multi-voice text-to-speech engine with prompt controls.
About EmotiVoice
EmotiVoice is an open-source text-to-speech engine from NetEase Youdao, distributed as a GitHub repository. It synthesizes English and Chinese speech using over 2000 voices and supports prompt-based control of emotion and style, including happy, excited, sad and angry. It provides a web interface, a scripting interface for batch generation, an OpenAI-compatible TTS API and a separate HTTP API.
It can be run through a Docker image, a full conda installation, or a hosted demo on Replicate, and a Mac app was released in December 2023. Voice cloning with personal data is supported alongside DataBaker and LJSpeech recipes. Support for additional languages such as Japanese and Korean is listed as under development.
Key features
- Emotional synthesis with prompts for happy, excited, sad and angry
- English and Chinese speech with over 2000 voices
- Web interface plus scripting interface for batch generation
- OpenAI-compatible TTS API and a separate HTTP API
- Voice cloning with personal data, DataBaker and LJSpeech recipes
- Docker image for local use on a machine with an NVIDIA GPU
Best for: Developers and researchers who need open-source English or Chinese speech synthesis with emotion and style control.
Good for
- Open source and described as available at no cost
- Prompt-based control over emotion and speaking style
- Several ways to run it: Docker, manual installation, web UI or hosted demo
Watch out for
- The Docker quickstart requires a machine with an NVIDIA GPU
- Japanese and Korean support is still listed as under development
- Pretrained model files must be downloaded separately before inference
EmotiVoice at a glance
- 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
EmotiVoice alternatives
Tools and sites you could use instead, ranked by how closely they match.
The whisper.cpp project ports OpenAI’s Whisper speech recognition model to C and C++.
Open source
24 alternatives
Audio-WebUI provides a web interface for different neural networks related to audio.
Open source
20 alternatives
TTS-WebUI is a Gradio and React interface with extensions for speech, audio, and music generation tools.
Open source
9 alternatives
Wispr Flow provides voice dictation that turns speech into text in text fields.
Vocol AI turns speech into text and shares AI-generated summaries, topic highlights and action items for voice collaboration.
Free trial
24 alternativesPopular in AI Voice & Audio
Well-known listings from the same topic.
Google Illuminateilluminate.google.comAlteredaltered.aiELSA Speakelsaspeak.comKreadoAIkreadoai.comPodwisepodwise.aiAddsubtitleaddsubtitle.ai
EmotiVoice FAQ
What languages does EmotiVoice speak?
It speaks both English and Chinese. Support for more languages, such as Japanese and Korean, is listed as under development.
Do I need a GPU to run it?
The Docker quickstart states that you need a machine with an NVIDIA GPU.
Can EmotiVoice clone a voice?
Yes. Voice cloning with personal data was released along with DataBaker and LJSpeech recipes.
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.