OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Stt

Stt is a locally run Python speech-recognition application that uses faster-whisper to transcribe speech in audio and video files. It exports plain text, JSON, or timestamped SRT subtitles and provides a browser interface, a local HTTP endpoint, and an OpenAI-compatible transcription interface.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Stt — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Stt when you want to transcribe audio or video on your own machine and choose among plain text, JSON, or timestamped SRT output. The browser interface supports file-based use; the documented local interfaces support software workflows.

Who it is for

  • People who need transcripts from audio or video files on a local computer.
  • Subtitle creators who need timestamped SRT output.
  • Developers seeking a locally hosted transcription interface for software workflows.

Documented uses

  • Convert speech in audio or video files into readable text.
  • Create timestamped SRT subtitles or JSON transcript output.
  • Send transcription requests to a local service through its documented HTTP or OpenAI-compatible interface.
Before you choose

Requirements & limits

The repository is public and specifies the GPL-3.0 license. The README describes a prebuilt Windows version and source deployment for Windows, Linux, and macOS.

  • The prebuilt release path is documented for Windows; other platform setup is described as source deployment.
  • Source setup requires Python 3.9–3.11, dependencies, FFmpeg, and a model in the models directory.
  • The included tiny model uses fewer resources than larger listed models; the README warns that large and large-v3 can exhaust memory without suitable GPU resources.
  • CUDA acceleration requires an NVIDIA GPU and correctly configured CUDA; CPU is the default.
  • The local endpoint and OpenAI-compatible interface are documented for connecting a locally running instance to other software.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Stt from source

Prepare a source installation and launch Stt’s local browser interface.

Before you start

  • Python 3.9–3.11
  • Git and a terminal
  • Project dependencies from requirements.txt
  • FFmpeg; on Windows, place ffmpeg.exe and ffprobe.exe in the project directory
  • A model folder in the project’s models directory

Steps

  1. Clone the repository into the directory where you want the project files.

  2. Create and activate a Python virtual environment, following the README’s platform-specific activation command.

  3. Install requirements with pip install -r requirements.txt.

  4. Add FFmpeg and download a model archive, placing its model folder in the project’s models directory.

  5. Run python start.py to open the local browser interface.

Expected outcome

A source installation starts Stt and opens its local browser interface.

Guide limitations

  • The README specifies Python 3.9–3.11.
  • The README gives different FFmpeg placement instructions for Windows versus Linux and macOS.
  • Model archives must be obtained and placed in the models directory separately.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
jianchang512/stt · Official homepage title · retained in its source language
How we review sourcesSuggest a correction