speakturbo-tts by emzod/speak-turbo
npx skills add https://github.com/emzod/speak-turbo --skill speakturbo-tts赋予你的代理实时与你对话的能力。超快速文本转语音,延迟约 90 毫秒,内置 8 种语音。
# 立即播放 - 你应该能通过扬声器听到 "Hello world"
speakturbo "Hello world"
# 输出: ⚡ 92ms → ▶ 93ms → ✓ 1245ms
# 通过保存到文件来验证是否正常工作
speakturbo "Hello world" -o test.wav
ls -lh test.wav # 应显示约 50-100KB 的文件
输出说明: ⚡ = 收到第一段音频,▶ = 开始播放,✓ = 完成
首次执行需要 2-5 秒,因为守护进程启动并将模型加载到内存中。后续调用到发出第一个声音约需 90 毫秒。
# 首次运行(较慢 - 守护进程启动中)
speakturbo "Starting up" # 约 2-5 秒
# 第二次运行(快速 - 守护进程已在运行)
speakturbo "Now I'm fast" # 约 90ms
# 基础用法 - 立即播放(默认语音:alba)
speakturbo "Hello world"
# 保存到文件(不播放音频)
speakturbo "Hello" -o output.wav
# 保存到指定文件
speakturbo "Goodbye" -o goodbye.wav
# 静默模式(抑制状态消息,仍播放音频)
speakturbo "Hello" -q
# 列出可用语音
speakturbo --list-voices
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 语音 | 类型 |
|---|---|
alba | 女声(默认) |
marius | 男声 |
javert | 男声 |
jean | 男声 |
fantine | 女声 |
cosette | 女声 |
eponine | 女声 |
azelma | 女声 |
| 指标 | 数值 |
|---|---|
| 首次发声时间 | 约 90ms(守护进程已预热) |
| 首次运行 | 2-5s(守护进程启动) |
| 实时因子 | 约快 4 倍 |
| 采样率 | 24kHz 单声道 |
speakturbo (Rust CLI, 2.2MB)
│
│ HTTP 流式传输 (端口 7125)
▼
speakturbo-daemon (Python + pocket-tts)
│
│ 模型在内存中,空闲 1 小时后自动关闭
▼
音频播放 (rodio)
speakturbo "She said \"hello\""-o 标志只允许写入白名单中的目录。默认情况下,这些目录是:
/tmp 和系统临时目录~/.speakturbo/如果你需要写入其他位置,请使用 --allow-dir:
speakturbo "Hello" -o /custom/path/audio.wav --allow-dir /custom/path
要永久允许一个目录,请将其添加到 ~/.speakturbo/config:
mkdir -p ~/.speakturbo && echo "/custom/path" >> ~/.speakturbo/config
配置文件每行一个目录。以 # 开头的行是注释。
| 代码 | 含义 |
|---|---|
| 0 | 成功(音频已播放/保存) |
| 1 | 错误(守护进程连接失败,参数无效) |
在以下情况下使用 speakturbo:
在以下情况下使用 speak:
speak "text" --voice ~/.chatter/voices/morgan_freeman.wav[laugh]、[sigh]完整用法请参阅 speak 技能文档。
没有音频播放:
# 检查守护进程是否在运行
curl http://127.0.0.1:7125/health
# 预期输出: {"status":"ready","voices":["alba","marius",...]}
# 通过保存到文件并手动播放来验证
speakturbo "test" -o /tmp/test.wav
afplay /tmp/test.wav # macOS
aplay /tmp/test.wav # Linux
守护进程无法启动:
# 检查端口可用性
lsof -i :7125
# 手动终止并重启
pkill -f "daemon_streaming"
speakturbo "test" # 自动重启守护进程
首次运行很慢: 这是正常现象。守护进程需要将约 100MB 的模型加载到内存中。后续调用会很快(约 90 毫秒)。
守护进程在首次使用时自动启动,并在空闲 1 小时后自动关闭。
# 检查状态
curl http://127.0.0.1:7125/health
# 手动停止
pkill -f "daemon_streaming"
# 查看日志
cat /tmp/speakturbo.log
| 功能 | speakturbo | speak |
|---|---|---|
| 首次发声时间 | 约 90ms | 约 4-8s |
| 语音克隆 | ❌ | ✅ |
| 情感标签 | ❌ | ✅ |
| 语音 | 8 种内置 | 自定义 wav 文件 |
| 引擎 | pocket-tts | Chatterbox |
每周安装量
946
仓库
GitHub 星标数
17
首次出现
2026 年 1 月 27 日
安全审计
安装于
github-copilot902
antigravity841
continue827
codebuddy825
opencode416
codex407
Give your agent the ability to speak to you real-time. Ultra-fast text-to-speech with ~90ms latency and 8 built-in voices.
# Play immediately - you should hear "Hello world" through your speakers
speakturbo "Hello world"
# Output: ⚡ 92ms → ▶ 93ms → ✓ 1245ms
# Verify it's working by saving to file
speakturbo "Hello world" -o test.wav
ls -lh test.wav # Should show ~50-100KB file
Output explained: ⚡ = first audio received, ▶ = playback started, ✓ = done
The first execution takes 2-5 seconds while the daemon starts and loads the model into memory. Subsequent calls are ~90ms to first sound.
# First run (slow - daemon starting)
speakturbo "Starting up" # ~2-5 seconds
# Second run (fast - daemon already running)
speakturbo "Now I'm fast" # ~90ms
# Basic - plays immediately (default voice: alba)
speakturbo "Hello world"
# Save to file (no audio playback)
speakturbo "Hello" -o output.wav
# Save to specific file
speakturbo "Goodbye" -o goodbye.wav
# Quiet mode (suppress status messages, still plays audio)
speakturbo "Hello" -q
# List available voices
speakturbo --list-voices
| Voice | Type |
|---|---|
alba | Female (default) |
marius | Male |
javert | Male |
jean | Male |
fantine | Female |
cosette | Female |
eponine |
| Metric | Value |
|---|---|
| Time to first sound | ~90ms (daemon warm) |
| First run | 2-5s (daemon startup) |
| Real-time factor | ~4x faster |
| Sample rate | 24kHz mono |
speakturbo (Rust CLI, 2.2MB)
│
│ HTTP streaming (port 7125)
▼
speakturbo-daemon (Python + pocket-tts)
│
│ Model in memory, auto-shutdown after 1hr idle
▼
Audio playback (rodio)
speakturbo "She said \"hello\""The -o flag only writes to directories that are on the allowlist. By default, these are:
/tmp and system temp directories~/.speakturbo/If you need to write elsewhere, use --allow-dir:
speakturbo "Hello" -o /custom/path/audio.wav --allow-dir /custom/path
To permanently allow a directory, add it to ~/.speakturbo/config:
mkdir -p ~/.speakturbo && echo "/custom/path" >> ~/.speakturbo/config
The config file is one directory per line. Lines starting with # are comments.
| Code | Meaning |
|---|---|
| 0 | Success (audio played/saved) |
| 1 | Error (daemon connection failed, invalid args) |
Use speakturbo when:
Usespeak instead when:
speak "text" --voice ~/.chatter/voices/morgan_freeman.wav[laugh], [sigh]See the speak skill documentation for full usage.
No audio plays:
# Check daemon is running
curl http://127.0.0.1:7125/health
# Expected: {"status":"ready","voices":["alba","marius",...]}
# Verify by saving to file and playing manually
speakturbo "test" -o /tmp/test.wav
afplay /tmp/test.wav # macOS
aplay /tmp/test.wav # Linux
Daemon won't start:
# Check port availability
lsof -i :7125
# Manually kill and restart
pkill -f "daemon_streaming"
speakturbo "test" # Auto-restarts daemon
First run is slow: This is expected. The daemon needs to load the ~100MB model into memory. Subsequent calls will be fast (~90ms).
The daemon auto-starts on first use and auto-shuts down after 1 hour idle.
# Check status
curl http://127.0.0.1:7125/health
# Manual stop
pkill -f "daemon_streaming"
# View logs
cat /tmp/speakturbo.log
| Feature | speakturbo | speak |
|---|---|---|
| Time to first sound | ~90ms | ~4-8s |
| Voice cloning | ❌ | ✅ |
| Emotion tags | ❌ | ✅ |
| Voices | 8 built-in | Custom wav files |
| Engine | pocket-tts | Chatterbox |
Weekly Installs
946
Repository
GitHub Stars
17
First Seen
Jan 27, 2026
Security Audits
Gen Agent Trust HubFailSocketPassSnykPass
Installed on
github-copilot902
antigravity841
continue827
codebuddy825
opencode416
codex407
AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具
40,200 周安装
| Female |
azelma | Female |