Boubou

chattts

Pipeline 2 languages Fixed speaker Mac only non-commercial

ChatTTS from 2Noise, a conversational voice trained on Chinese and English. It has no named voices, so Boubou picked one speaker from the model and uses it every time.

npx boubou@beta run chattts:en

Talk on this Mac. It needs Node.js 18 or later; Get started walks you through.

Talk on this Linux PC. It needs an NVIDIA GPU, and the first run also downloads a 3.62 GB engine that every pipeline voice shares; Get started walks you through.

npx boubou@beta serve chattts:en

Talk from a phone on the same Wi-Fi, or connect a robot or app. The model still runs on this Mac. Phones and robots walks you through.

Talk from a phone on the same Wi-Fi, or connect a robot or app. The model still runs on this PC. Phones and robots walks you through.

chattts runs on Apple Silicon Macs only. Other models run on Linux.

Download
6.80 GB
Memory, estimated
—
Speaks
English
Voice
Fixed speaker

Recommended device

Apple Silicon Mac

  • No memory estimate for this version yet
  • macOS 15 or later
  • Qwen3.5-4B, the language model Boubou maintains
  • The voice runs on the CPU

Memory needs are estimates. Boubou checks the machine before it downloads anything, and smaller machines still need testing.

Voices and languages

Everything the model can speak, as its own card or files list it. Black marks what Boubou uses.

  • Boubou uses
  • Available in the model

Languages

2 languages

EnglishChinese

The Whisper version hears Chinese or English and answers in the same language.

Source: 2noise/ChatTTS v0.2.5 README

Voices

Fixed speaker

ChatTTS has no preset voices and would sample a new speaker at every start. Boubou ships one speaker sampled from the model, so every reply and every start sounds the same.

Source: 2noise/ChatTTS v0.2.5 README

Versions 2

A version is one ready-to-run setup with its own command. Versions differ in size, language or the models they combine. Suggested ones also appear in the boubou menu.

VersionWhat’s differentSpeaksVoiceDownloadMac
English, with the Parakeet recognizerEnglishFixed speaker6.80 GB—
Hears and answers in English or ChineseEnglish or ChineseFixed speaker5.91 GB—

How it works

You speak
VAD

Silero + Smart Turn v3.2

--vad silero
STT

Parakeet TDT 0.6B v3

speech to text
LLM

Qwen3.5-4B · 4-bit

--llm_backend mlx-lm
TTS

chattts · Fixed speaker

--tts chatTTS
It answers

Boubou owns the microphone and speakers. Apple voice processing cancels echo, so you can talk over a reply. Boubou drops the queued audio and cancels the generation.

Swap a component

Boubou maintains one Hugging Face speech-to-speech 1.1.0 pipeline and pins every model in it. Add an upstream option after the model to replace one part.

Change the language model to any MLX model on Hugging Face

npx boubou@beta run chattts:en --model_name mlx-community/Llama-3.2-3B-Instruct-4bit

Change speech recognition to Whisper

npx boubou@beta run chattts:en --stt mlx-audio-whisper

Options work with serve too. Boubou does not check the models you name: they download from Hugging Face into your own Hugging Face cache. API modules send audio or text to the server you configure.

  • Used by Boubou
  • Also runs in Boubou

VADVoice activity

--vad

Hears when you start and stop talking. Smart Turn v3.2 then decides whether a pause ends your turn.

silero

Not in Boubou’s runtime yet: firered

STTSpeech to text

--stt

Writes down what you said. Parakeet is the default; Whisper versions detect the language.

parakeet-tdtmlx-audio-whisperwhisperqwen3-asrvllm-realtimeAPIopenaiAPIopenai-realtimeAPI

Not in Boubou’s runtime yet: faster-whisper, whisper-mlx, parakeet-unified, nemotron-streaming, orukeet, paraformer, sense-voice

LLMLanguage model

--llm_backend

Writes the reply. Boubou runs pinned 4-bit Qwen3.5 models with mlx-lm; --model_name picks another one.

mlx-lmtransformerschat-completionsAPIresponses-apiAPI

TTSText to speech

--tts

Speaks the reply while it is still being written. Every pipeline voice in the library is one of these.

qwen3kokoropocketphononkittensupertonicchatTTSfacebookMMSomnivoicedrama3openaiAPIminimaxAPI

License

CC BY-NC 4.0: non-commercial use only. Read the license. Weights keep their own licenses; check them before commercial use.

Sources