How do I install the Tts Router skill?

Run npx skillmds@latest add dvcrn/tts-router in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Tts Router safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Tts Router?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Tts Router free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Tts Router?

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Tts Router by dvcrn — Agent Skill

Name: Tts Router
Rating: 4.5 (4 reviews)
Author: dvcrn

Tts Router

Local TTS router for Apple Silicon — pull models, serve OpenAI-compatible API, synthesize speech, clone voices. Use when the user asks to "generate speech", "text to speech", "start TTS server", "pull a TTS model", "clone a voice", "speak in someone's voice", or any task involving local speech synthesis on macOS.

dvcrn Updated Sep 8, 2026 32 repo stars

File contents

tts-router — Local TTS Router for Apple Silicon

A CLI that manages and serves multiple TTS models locally on Apple Silicon (MLX). Models are downloaded from HuggingFace Hub and served via OpenAI + DashScope compatible APIs.

Prerequisites

macOS with Apple Silicon (M1/M2/M3/M4)
uv installed — see https://docs.astral.sh/uv/getting-started/installation/ (e.g. brew install uv or via the official installer)
ffmpeg installed (brew install ffmpeg)

Install

# From PyPI (requires --prerelease=allow due to mlx-audio upstream dep)
uvx --prerelease=allow tts-router list

# Or install with pip
pip install tts-router

Commands

`tts-router list` — Show available models

tts-router list

`tts-router pull <model>` — Download model weights

tts-router pull qwen3-tts
tts-router pull kokoro

Models are cached in ~/.cache/huggingface/hub/. No need to re-download.

`tts-router serve` — Start the TTS API server

# Default: qwen3-tts on port 8091
tts-router serve

# Custom model and port
tts-router serve --model kokoro --port 9000

The server requires models to be pulled first.

`tts-router say` — Synthesize speech from CLI

tts-router say "Hello world" -o hello.wav
tts-router say "Hello" --voice Vivian --model kokoro -o out.wav

Available Models

Short Name	Features
`qwen3-tts`	multi-speaker, emotion, instruct (default)
`qwen3-tts-design`	free-form voice description
`qwen3-tts-clone`	voice cloning with ref audio
`kokoro`	fast, lightweight, multi-lang
`dia`	multi-speaker dialogue, laughter/emotion sounds
`chatterbox`	23 languages, emotion control, voice cloning
`orpheus`	emotive TTS with emotion tags

Quick Start for Agent

# 1. Pull the default model
tts-router pull qwen3-tts

# 2. Start the server
tts-router serve

# 3. Generate speech (OpenAI format)
curl -X POST http://localhost:8091/v1/audio/speech \
  -H "Content-Type: application/json" \
  -d '{"input": "Hello world", "voice": "Vivian"}' \
  --output output.wav

API Endpoints (when serving)

Endpoint	Method	Description
`GET /`	GET	Playground UI
`POST /v1/audio/speech`	POST	OpenAI-compatible TTS
`GET /v1/audio/voices`	GET	List available voices
`GET /health`	GET	Health check
`POST /v1/audio/clone`	POST	Voice clone generation
`POST /v1/audio/references/upload`	POST	Upload reference audio
`POST /v1/audio/references/from-url`	POST	Fetch ref audio by URL

Advanced Use Cases

For more complex workflows, read the relevant reference file:

Clone a voice from any URL (YouTube, Bilibili, podcast, direct audio link) → read references/voice-cloning.md
Use tts-router as a TTS provider in OpenClaw → read references/openclaw.md

---name: tts-routerdescription: Local TTS router for Apple Silicon — pull models, serve OpenAI-compatible API, synthesize speech, clone voices. Use when the user asks to "generate speech", "text to speech", "start TTS server", "pull a TTS model", "clone a voice", "speak in someone's voice", or any task involving local speech synthesis on macOS.---# tts-router — Local TTS Router for Apple SiliconA CLI that manages and serves multiple TTS models locally on Apple Silicon (MLX).Models are downloaded from HuggingFace Hub and served via OpenAI + DashScope compatible APIs.## Prerequisites- macOS with Apple Silicon (M1/M2/M3/M4)- `uv` installed — see https://docs.astral.sh/uv/getting-started/installation/ (e.g. `brew install uv` or via the official installer)- ffmpeg installed (`brew install ffmpeg`)## Install```bash# From PyPI (requires --prerelease=allow due to mlx-audio upstream dep)uvx --prerelease=allow tts-router list# Or install with pippip install tts-router```## Commands### `tts-router list` — Show available models```bashtts-router list```### `tts-router pull <model>` — Download model weights```bashtts-router pull qwen3-ttstts-router pull kokoro```Models are cached in `~/.cache/huggingface/hub/`. No need to re-download.### `tts-router serve` — Start the TTS API server```bash# Default: qwen3-tts on port 8091tts-router serve# Custom model and porttts-router serve --model kokoro --port 9000```The server requires models to be pulled first.### `tts-router say` — Synthesize speech from CLI```bashtts-router say "Hello world" -o hello.wavtts-router say "Hello" --voice Vivian --model kokoro -o out.wav```## Available Models| Short Name | Features || ------------------ | ----------------------------------------------- || `qwen3-tts` | multi-speaker, emotion, instruct (default) || `qwen3-tts-design` | free-form voice description || `qwen3-tts-clone` | voice cloning with ref audio || `kokoro` | fast, lightweight, multi-lang || `dia` | multi-speaker dialogue, laughter/emotion sounds || `chatterbox` | 23 languages, emotion control, voice cloning || `orpheus` | emotive TTS with emotion tags |## Quick Start for Agent```bash# 1. Pull the default modeltts-router pull qwen3-tts# 2. Start the servertts-router serve# 3. Generate speech (OpenAI format)curl -X POST http://localhost:8091/v1/audio/speech \ -H "Content-Type: application/json" \ -d '{"input": "Hello world", "voice": "Vivian"}' \ --output output.wav```## API Endpoints (when serving)| Endpoint | Method | Description || ------------------------------------ | ------ | ------------------------- || `GET /` | GET | Playground UI || `POST /v1/audio/speech` | POST | OpenAI-compatible TTS || `GET /v1/audio/voices` | GET | List available voices || `GET /health` | GET | Health check || `POST /v1/audio/clone` | POST | Voice clone generation || `POST /v1/audio/references/upload` | POST | Upload reference audio || `POST /v1/audio/references/from-url` | POST | Fetch ref audio by URL |## Advanced Use CasesFor more complex workflows, read the relevant reference file:- **Clone a voice from any URL** (YouTube, Bilibili, podcast, direct audio link) → read `references/voice-cloning.md`- **Use tts-router as a TTS provider in OpenClaw** → read `references/openclaw.md`

Frequently asked questions