# devnen/Chatterbox-TTS-Server

Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale text processing. Runs accelerated on NVIDIA (CUDA), AMD (ROCm), and CPU.

Repository: https://github.com/devnen/Chatterbox-TTS-Server
Canonical: https://ross.abutalabs.com/products/chatterbox-tts-server
Homepage: https://colab.research.google.com/github/devnen/Chatterbox-TTS-Server/blob/main/Chatterbox_TTS_Colab_Demo.ipynb
Language: Python
License: MIT
License Family: permissive
Topics: ai, api-server, audio-generation, chatterbox, cuda, fastapi, huggingface, openai-api, python, pytorch, speech-synthesis, speech-synthesis-api, text-to-speech, tts, tts-api, voice-cloning, web-ui, chatterbox-tts, rocm
Last push: 2026-05-26T19:49:30+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 84, release rhythm 59, longevity 32
- inputs: {"age_days": 459, "days_push": 99, "days_rel": 114, "gap_med": 146, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1420, forks 350 (observed 2026-08-28T04:04:40.369138+00:00)

## What it is
A self-hosted server wrapping Resemble AI's Chatterbox TTS models behind an OpenAI-compatible API with a modern web UI. It supports voice cloning, built-in voices, seed-based reproducibility, and large-scale text processing like audiobook generation, accelerated on CUDA, ROCm, MPS, or CPU.

## Use cases
- self-host a text-to-speech API server
- clone a voice from an audio sample
- generate audiobooks from long text documents
- use an OpenAI-compatible TTS endpoint with existing tools
- generate expressive speech with paralinguistic tags like [laugh]
- run TTS locally on NVIDIA or AMD GPUs
- create consistent character voices for narration

## When to choose
- you want to self-host Chatterbox TTS with a ready-made UI and API
- you need OpenAI-compatible TTS endpoints for drop-in integration
- you need voice cloning and audiobook-scale chunked text processing
- you want GPU acceleration across NVIDIA, AMD, or Apple Silicon

## When to avoid
- you need a lightweight TTS without GPU or model download overhead
- you want a managed cloud TTS service rather than self-hosting
- you need real-time streaming TTS with sub-100ms latency
- you require languages outside Chatterbox's supported set on the original model

## Facets
- artifact type: service
- maturity: active
- function: tts, http-server, api-framework, llm-inference, audio-processing
- domain: speech-processing, artificial-intelligence, self-hosted, apis
- platform: self-hosted, python, cross-platform
- tags: text-to-speech, voice-cloning, openai-compatible-api, audiobook-generation, chatterbox, fastapi, cuda, rocm, web-ui, audio, docker, gpu, web-server

## Member repositories
- devnen/Chatterbox-TTS-Server (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:40.369138+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 2026-08-30T04:37:48.519989+00:00, confidence not recorded.
  - readme: https://github.com/devnen/Chatterbox-TTS-Server (fetched 2026-08-28T04:04:40.369138+00:00, sha 576c53e7f6b8)
  - homepage: https://colab.research.google.com/github/devnen/Chatterbox-TTS-Server/blob/main/Chatterbox_TTS_Colab_Demo.ipynb (fetched 2026-08-29T11:50:06.112762+00:00, sha cbaa090f147c)
- Data as of 2026-08-30T08:39:29.467469+00:00.