Speech analysis

Speech analysis

Runs two audEERING wav2vec2 models on a speech recording, one for emotion and one for age and gender, and ships four sample clips to try. A Gradio demo for speech researchers. Non-commercial license.

Made by audeering on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This is a Gradio demo from audEERING that analyzes speech. It names two large wav2vec2 models, one for emotion and one for age and gender. Four sample clips come with it, and their names give a speaker's gender, age and mood. The README is empty, so the details below come from the model names and the file list. It runs on the basic CPU tier at Hugging Face.

Who it suits: Speech researchers who want to try emotion and age-gender models on a clip, and developers who want a small example of audio models in Gradio.

Industry | Who uses it | How they use it | Example
Research | Speech researchers | Try both models on a clip without setup | Run the bundled sad sample and read the output
Software | Developers | Read app.py to see how audio reaches the models | Reuse the layout in their own voice app
Education | Students | See what speech models can estimate | Compare the happy and angry samples
Analytics | Voice analytics teams | Test emotion scoring on recordings they may analyze | Check how a consented recording scores

Skip it if you need commercial use, since the license is a non-commercial one.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• Windows, macOS or Linux with Python, as a local copy

Use case | Who | What they get back
Estimate emotion from speech | Researchers | The emotion model's output for your clip
Estimate age and gender | Researchers | The second model's output for the same clip
Try the bundled samples | Newcomers | Results for four short clips of known gender, age and mood

How to set it up:

• Nothing at all if you only use the online Space
• Python and pip, for a local copy
• The Python packages listed in requirements.txt

1. Open the Space's page at Hugging Face to use it online.
2. For a local copy, install the Hugging Face hub package and download the Space.
3. Move into the new folder and install Gradio at the pinned version.
4. Install the packages from requirements.txt.
5. Start the app with Python.

pip install -U huggingface_hub
hf download audeering/speech-analysis --repo-type space --local-dir speech-analysis
cd speech-analysis
pip install gradio==4.42.0
pip install -r requirements.txt
python app.py

The repository holds the app file, the requirements file and the four sample recordings. The page does not say what a local run needs beyond the packages.

How to use it: Online, open the Space and give it a recording or pick one of the bundled samples. On your own machine, run the app file and open the page Gradio serves in your browser. The page lists no other commands.

Tool | What it does
python app.py | Starts the Gradio app on your computer

Example: You open the Space and pick the bundled sample named for a 27-year-old man who sounds sad. The app returns its estimates for emotion and for age and gender, and you compare them with what the file name tells you.

For newcomers and experts: If you are new, start with the four bundled clips. Their names say who is speaking and in what mood, so you can see how the models respond before you use your own audio.

If you know the field, both models are large wav2vec2 variants fine-tuned by audEERING. The page gives no scores, label definitions or training data, so read the model pages before relying on the numbers.

Open the Space in a browser
Add a recording or pick a sample
The emotion model reads the speech
The age and gender model reads it too
The estimates are shown

Good to know:

• License: cc-by-nc-4
• Cost to run: none named, and the Space sits on the basic CPU tier at Hugging Face
• Data it reaches: the audio you give it, and the two model files from Hugging Face
• Not for: commercial use, or analyzing a person's voice without their permission

On Hugging Face, 13 November 2026

• Likes: 3
• Built with: gradio
• License: cc-by-nc-4.0

Links

• Space: https://huggingface.co/spaces/audeering/speech-analysis
• Files: https://huggingface.co/spaces/audeering/speech-analysis/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.