# erew123/alltalk_tts

AllTalk is based on the Coqui TTS engine, similar to the Coqui_tts extension for Text generation webUI, however supports a variety of advanced features, such as a settings page, low VRAM support, DeepSpeed, narrator, model finetuning, custom models, wav file maintenance. It can also be used with 3rd Party software via JSON calls.

Repository: https://github.com/erew123/alltalk_tts
Canonical: https://ross.abutalabs.com/products/alltalk_tts
Language: HTML
License: AGPL-3.0
License Family: copyleft
Last push: 2026-01-09T08:58:55+00:00

## Health v2 (maintenance only)
Score: 44/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 61, release rhythm 8, longevity 71
- inputs: {"age_days": 999, "days_push": 236, "days_rel": 555, "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 2429, forks 285 (observed 2026-08-28T04:06:50.996951+00:00)

## What it is
AllTalk TTS is a text-to-speech application built on the Coqui TTS engine, usable standalone or as an extension for Text-generation-webui, SillyTavern, and KoboldCPP. It offers advanced features like model finetuning, DeepSpeed acceleration, low VRAM mode, multi-voice narration, and a JSON API for third-party integration.

## Use cases
- generate speech from text locally with a gpu
- add tts voices to sillytavern or text-generation-webui
- clone a custom voice and finetune a tts model
- generate audiobooks with separate narrator and character voices
- run text-to-speech on a low vram gpu alongside an llm
- integrate tts into third-party apps via a json api

## When to choose
- you want local, self-hosted text-to-speech with xttsv2 models
- you need voice finetuning or multi-voice narration
- you use text-generation-webui, SillyTavern, or KoboldCPP and want tts integration
- you have limited vram or want DeepSpeed speedups

## When to avoid
- you need a managed cloud tts service
- you have no gpu and need very fast synthesis
- you need a lightweight library to embed rather than a full application

## Facets
- artifact type: application
- maturity: active
- function: tts, speech-recognition, llm-inference, api-framework, audio-processing
- domain: speech-processing, artificial-intelligence, large-language-models
- platform: windows, python, self-hosted
- tags: coqui-tts, xttsv2, text-to-speech, deepspeed, sillytavern, text-generation-webui, voice-cloning, narration, audio, linux, gpu

## Member repositories
- erew123/alltalk_tts (main) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:50.996951+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 2026-08-30T02:31:27.338538+00:00, confidence not recorded.
  - readme: https://github.com/erew123/alltalk_tts (fetched 2026-08-28T04:06:50.996951+00:00, sha 1318cb3d75ce)
- Data as of 2026-08-30T08:39:29.467469+00:00.