Practical overview
When it fits
Use Speech AI Forge when you want to run speech-generation models through a browser interface or expose them through a separate API service, especially when the workflow also needs voice controls, SSML preparation or related audio tools.
Who it is for
- People who want an interactive interface for generating speech with supported models.
- Developers who need a standalone API server for speech-generation workflows.
- Users preparing long-form, multi-speaker or subtitle-based audio scripts.
Documented uses
- Generate speech from text and adjust voice, style, speed, pitch or volume.
- Create long-form speech with automatic text splitting or SSML scripts.
- Build, test or customize voices using supported voice-management tools.
- Convert speech to text or align recognized speech with a script using the listed ASR tools.
Requirements & limits
The repository is public and licensed under AGPL-3.0. The project documents local, Docker, Colab and Windows-package routes; local setup requires dependencies and model files.
- The project separates the Gradio interface (
webui.py) from its API server (launch.py), so users can choose an interactive or programmatic workflow. - Its README lists multiple supported TTS model families, including ChatTTS, CosyVoice, FishSpeech, GPT-SoVITS and F5-TTS; model availability and language support vary by model.
- Local use requires installing dependencies and downloading the chosen models before starting the interface.
- The README provides Docker Compose configurations for the web interface and API as separate services.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Start the local web interface
Prepare the documented local prerequisites and launch the Gradio interface.
Before you start
- Python environment for the project
- Project dependencies installed
- Required model files downloaded
Steps
Follow the project’s dependency instructions.
Download the model files required for the intended use.
Run the command below from the project.
python webui.py
Expected outcome
The project’s Gradio web interface starts for interactive speech-generation workflows.
Guide limitations
- The required dependencies and model files vary by setup; the cited instructions do not specify a universal hardware requirement.
Launch the API server and inspect its endpoints
Start the standalone API service and open its documented endpoint listing.
Before you start
- Project dependencies installed
- Required model files downloaded
Steps
Run the command below from the project.
python launch.pyOpen
http://localhost:7870/docsto view the endpoints enabled for that server.
Expected outcome
The API server starts, and its enabled endpoints can be viewed in the local documentation page.
Guide limitations
- The README notes that launch parameters can be checked with
python launch.py -h; API use beyond endpoint discovery is not covered by these steps.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 12 October 2026
- Original website title
- lenML/Speech-AI-Forge · Official homepage title · retained in its source language