# synesthesiam/opentts

Open Text to Speech Server

Repository: https://github.com/synesthesiam/opentts
Canonical: https://ross.abutalabs.com/products/opentts
Language: Python
License: MIT
License Family: permissive
Archived: true
Last push: 2024-03-20T15:34:46+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2296, "days_push": 896, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1118, forks 160 (observed 2026-08-28T04:03:39.190764+00:00)

## What it is
OpenTTS is a text-to-speech server that unifies access to multiple open source TTS systems (Larynx, Glow-Speak, Coqui-TTS, MaryTTS, flite, Festival) and their voices across many languages. It exposes an HTTP API with a web interface and supports a subset of SSML for mixing voices, systems, and languages within a single request.

## Use cases
- self-host a text to speech server with multiple voices
- generate speech audio from text via an HTTP API
- mix different TTS engines and languages in one document with SSML
- find and preview open source TTS voices for many languages
- add offline text-to-speech to a home automation setup

## When to choose
- you want one unified API over many open source TTS engines and voices
- you need multilingual speech synthesis with per-sentence language switching
- you prefer self-hosted, offline TTS with Docker deployment

## When to avoid
- you need the latest neural TTS models or active development, since the project is in maintenance mode
- you need commercial-quality cloud voices or cloud provider integrations
- you only need a single TTS engine, where using that engine directly is simpler

## Facets
- artifact type: service
- maturity: maintenance
- function: tts, http-server, speech-recognition
- domain: speech-processing, self-hosted
- platform: python, self-hosted
- tags: text-to-speech, ssml, voice-synthesis, multilingual, rest-api, natural-language-processing, docker, web-server

## Member repositories
- synesthesiam/opentts (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:39.190764+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 2026-08-30T06:41:50.541690+00:00, confidence not recorded.
  - readme: https://github.com/synesthesiam/opentts (fetched 2026-08-28T04:03:39.190764+00:00, sha 8390cca68eff)
- Data as of 2026-08-30T08:39:29.467469+00:00.