# travisvn/openai-edge-tts

Free, high-quality text-to-speech API endpoint to replace OpenAI, Azure, or ElevenLabs

Repository: https://github.com/travisvn/openai-edge-tts
Canonical: https://ross.abutalabs.com/products/openai-edge-tts
Homepage: https://tts.travisvn.com
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: ai, chatgpt, edge-tts, llm, llm-webui, llms, ollama, ollama-webui, open-webui, openai, speech, text-to-speech, tts, self-hosted, claude, gpt, local-llm, azure, elevenlabs
Last push: 2025-07-01T23:56:27+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 29, release rhythm 8, longevity 49
- inputs: {"age_days": 693, "days_push": 428, "days_rel": 613, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2066, forks 313 (observed 2026-08-28T04:06:10.055012+00:00)

## What it is
A self-hosted Python service that emulates the OpenAI text-to-speech API endpoint (/v1/audio/speech) using Microsoft Edge's free online TTS service via edge-tts. It supports OpenAI voice mappings, multiple audio formats, adjustable playback speed, and SSE streaming, deployable via Docker.

## Use cases
- replace OpenAI TTS API with a free self-hosted alternative
- generate speech from text without paying for Azure or ElevenLabs
- add text-to-speech to an Open WebUI or Ollama chat interface
- stream audio responses in real time via SSE
- convert text to mp3, wav, opus, aac, flac, or pcm audio
- use Microsoft Edge neural voices through an OpenAI-compatible endpoint

## When to choose
- you need an OpenAI-compatible /v1/audio/speech endpoint without API costs
- you want high-quality neural voices for free using Edge's online service
- you're self-hosting LLM tools like Open WebUI and need TTS integration
- you need multiple audio formats and adjustable playback speed

## When to avoid
- you need fully offline TTS since edge-tts relies on Microsoft's online service
- you require OpenAI's exact voice quality or voice cloning
- you need a client library rather than a hosted API service
- commercial use is a concern given the GPL-3.0 license and reliance on Microsoft's service

## Facets
- artifact type: service
- maturity: active
- function: tts, http-server, api-framework, audio-processing, self-hosted
- domain: speech-processing, artificial-intelligence, self-hosted, apis
- platform: self-hosted, python, cross-platform
- tags: openai-compatible, edge-tts, text-to-speech, api-endpoint, audio-streaming, sse, drop-in-replacement, audio, docker, web-server

## Member repositories
- travisvn/openai-edge-tts (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:10.055012+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:56:54.460239+00:00, confidence not recorded.
  - readme: https://github.com/travisvn/openai-edge-tts (fetched 2026-08-28T04:06:10.055012+00:00, sha be469bbf7db2)
  - homepage: https://tts.travisvn.com (fetched 2026-08-29T10:37:12.282438+00:00, sha 788dbd727b9e)
- Data as of 2026-08-30T08:39:29.467469+00:00.