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

Openai Edge Tts

Openai Edge Tts is a Python-based text-to-speech API that uses Edge-TTS and emulates OpenAI’s `/v1/audio/speech` endpoint.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Openai Edge Tts — 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 it when an application needs an OpenAI-style text-to-speech endpoint backed by Edge-TTS, and its supported voices, formats and request behavior fit the integration.

Who it is for

  • Developers integrating speech generation into applications that use an OpenAI-compatible TTS request format.
  • Operators configuring a text-to-speech endpoint for an AI assistant, chatbot or LLM interface.

Documented uses

  • Convert text of up to 4,096 characters into audio.
  • Select a mapped OpenAI voice or an Edge-TTS voice, an output format and playback speed.
  • Return audio directly or stream it using Server-Sent Events.
Before you choose

Requirements & limits

  • The API emulates /v1/audio/speech and supports raw audio or SSE streaming.
  • Listed output formats are MP3, Opus, AAC, FLAC, WAV and PCM; FFmpeg is needed for format conversion and is absent from the default local Compose build.
  • Playback speed can be set from 0.25× to 4×, and the request text limit is 4,096 characters.
  • The instructions parameter for fine-tuning voice characteristics is not supported.
  • The service uses Microsoft Edge’s online text-to-speech service.

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 the API with Docker Compose

Prepare and start the service using the repository’s documented Docker Compose setup.

Before you start

  • Docker and Docker Compose
  • A local copy of the repository

Steps

  1. Clone the repository and change into its directory.

  2. Create a root .env file, or copy .env.example to .env.

  3. Run the command below.

    Documented command
    docker compose up --build

Expected outcome

The README says the server is accessible at `http://localhost:5050`.

Guide limitations

  • The default local Docker Compose build does not include FFmpeg; FFmpeg is needed for audio format conversion, while MP3 use does not require it.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
travisvn/openai-edge-tts · Official homepage title · retained in its source language
How we review sourcesSuggest a correction