audiomind

Name: audiomind
Author: wells1137

11installs1forks

How to install audiomind?

wells1137/media-skills/audiomind

$npx -y skills add wells1137/media-skills --skill audiomind

Installs into the current project.

Summary

Tired of juggling multiple audio APIs? This skill gives you one-command access to TTS, music generation, sound effects, and voice cloning. Use when you want to generate any audio without managing multiple API keys.

Files · 1

View on GitHub

SKILL.md

1	# 🎙️ AudioMind
2
3	Use when: User asks to generate speech, narrate text, create a voice-over, compose music, or produce a sound effect.
4
5	AudioMind is a smart audio dispatcher. It analyzes your request and routes it to the best available model — ElevenLabs for speech and music, fal.ai for fast SFX — and returns a ready-to-use audio URL.
6
7	---
8
9	## Quick Reference
10
11	\| Request Type \| Best Model \| Latency \|
12	\|---\|---\|---\|
13	\| Narrate text / Voice-over \| `elevenlabs-tts-v3` \| ~3s \|
14	\| Low-latency TTS (real-time) \| `elevenlabs-tts-turbo` \| <1s \|
15	\| Background music \| `cassetteai-music` \| ~15s \|
16	\| Sound effect \| `elevenlabs-sfx` \| ~5s \|
17	\| Clone a voice from audio \| `elevenlabs-voice-clone` \| ~10s \|
18
19	---
20
21	## How to Use
22
23	### 1. Start the AudioMind server (once per session)
24
25	```bash
26	bash {baseDir}/tools/start_server.sh
27	```
28
29	This starts the ElevenLabs MCP server on port 8124. The skill uses it for all audio generation.
30
31	### 2. Route the request
32
33	Analyze the user's request and call the appropriate tool via the MCP server:
34
35	Text-to-Speech (TTS)
36
37	When user asks to "narrate", "read aloud", "say", or "create a voice-over":
38
39	```
40	Use MCP tool: text_to_speech
41	text: "<the text to narrate>"
42	voice_id: "JBFqnCBsd6RMkjVDRZzb" # Default: "George" (professional, neutral)
43	model_id: "eleven_multilingual_v2" # Use "eleven_turbo_v2_5" for low latency
44	```
45
46	Music Generation
47
48	When user asks to "compose", "create background music", or "make a soundtrack":
49
50	```
51	Use MCP tool: text_to_sound_effects (via cassetteai-music on fal.ai)
52	prompt: "<music description, e.g. 'upbeat lo-fi hip hop, 90 seconds'>"
53	duration_seconds: <duration>
54	```
55
56	Sound Effect (SFX)
57
58	When user asks for a specific sound (e.g., "a door creaking", "rain on a window"):
59
60	```
61	Use MCP tool: text_to_sound_effects
62	text: "<sound description>"
63	duration_seconds: <1-22>
64	```
65
66	Voice Cloning
67
68	When user provides an audio sample and wants to clone the voice:
69
70	```
71	Use MCP tool: voice_add
72	name: "<voice name>"
73	files: ["<audio_file_url>"]
74	```
75
76	---
77
78	## Example Conversations
79
80	User: "帮我把这段文字配音：欢迎来到我们的产品发布会"
81
82	```
83	→ Route to: text_to_speech
84	text: "欢迎来到我们的产品发布会"
85	voice_id: "JBFqnCBsd6RMkjVDRZzb"
86	model_id: "eleven_multilingual_v2"
87	```
88
89	> 🎙️ 配音完成！[点击收听](audio_url)
90
91	---
92
93	User: "给我生成一段 60 秒的轻松背景音乐，适合播客"
94
95	```
96	→ Route to: cassetteai-music (fal.ai)
97	prompt: "relaxing lo-fi background music for a podcast, gentle piano and soft beats, 60 seconds"
98	duration_seconds: 60
99	```
100
101	> 🎵 背景音乐生成完成！[点击收听](audio_url)
102
103	---
104
105	User: "生成一个科幻风格的门开启音效"
106
107	```
108	→ Route to: text_to_sound_effects
109	text: "a futuristic sci-fi door sliding open with a hydraulic hiss"
110	duration_seconds: 3
111	```
112
113	---
114
115	## Setup
116
117	### Required
118
119	Set `ELEVENLABS_API_KEY` in `~/.openclaw/openclaw.json`:
120
121	```json
122	{
123	"skills": {
124	"entries": {
125	"audiomind": {
126	"enabled": true,
127	"env": {
128	"ELEVENLABS_API_KEY": "your_elevenlabs_key_here"
129	}
130	}
131	}
132	}
133	}
134	```
135
136	Get your key at [elevenlabs.io/app/settings/api-keys](https://elevenlabs.io/app/settings/api-keys).
137
138	### Optional (for fal.ai music & SFX models)
139
140	```json
141	"FAL_KEY": "your_fal_key_here"
142	```
143
144	Get your key at [fal.ai/dashboard/keys](https://fal.ai/dashboard/keys).
145
146	---
147
148	## Self-Hosting the Proxy
149
150	The `cli.js` connects to a hosted proxy by default. If you want full control — or need to serve users in regions where `vercel.app` is blocked — you can deploy your own instance from the `proxy/` directory.
151
152	### Quick Deploy (Vercel)
153
154	```bash
155	cd proxy
156	npm install
157	vercel --prod
158	```
159
160	### Environment Variables
161
162	Set these in your Vercel project (Dashboard → Settings → Environment Variables):
163
164	\| Variable \| Required For \| Where to Get \|
165	\|---\|---\|---\|
166	\| `ELEVENLABS_API_KEY` \| TTS, SFX, Voice Clone \| [elevenlabs.io/app/settings/api-keys](https://elevenlabs.io/app/settings/api-keys) \|
167	\| `FAL_KEY` \| Music generation \| [fal.ai/dashboard/keys](https://fal.ai/dashboard/keys) \|
168	\| `VALID_PRO_KEYS` \| (Optional) Restrict access \| Comma-separated list of allowed client keys \|
169
170	### Point cli.js to Your Proxy
171
172	```bash
173	export AUDIOMIND_PROXY_URL="https://your-domain.com/api/audio"
174	```
175
176	Or set it in `~/.openclaw/openclaw.json`:
177
178	```json
179	{
180	"skills": {
181	"entries": {
182	"audiomind": {
183	"env": {
184	"AUDIOMIND_PROXY_URL": "https://your-doma

People who liked this also viewed

6 picks

Type

audiomind

11installs1forks

View on GitHub

How to install audiomind?

wells1137/media-skills/audiomind

$npx -y skills add wells1137/media-skills --skill audiomind

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# 🎙️ AudioMind
2
3	Use when: User asks to generate speech, narrate text, create a voice-over, compose music, or produce a sound effect.
4
5	AudioMind is a smart audio dispatcher. It analyzes your request and routes it to the best available model — ElevenLabs for speech and music, fal.ai for fast SFX — and returns a ready-to-use audio URL.
6
7	---
8
9	## Quick Reference
10
11	\| Request Type \| Best Model \| Latency \|
12	\|---\|---\|---\|
13	\| Narrate text / Voice-over \| `elevenlabs-tts-v3` \| ~3s \|
14	\| Low-latency TTS (real-time) \| `elevenlabs-tts-turbo` \| <1s \|
15	\| Background music \| `cassetteai-music` \| ~15s \|
16	\| Sound effect \| `elevenlabs-sfx` \| ~5s \|
17	\| Clone a voice from audio \| `elevenlabs-voice-clone` \| ~10s \|
18
19	---
20
21	## How to Use
22
23	### 1. Start the AudioMind server (once per session)
24
25	```bash
26	bash {baseDir}/tools/start_server.sh
27	```
28
29	This starts the ElevenLabs MCP server on port 8124. The skill uses it for all audio generation.
30
31	### 2. Route the request
32
33	Analyze the user's request and call the appropriate tool via the MCP server:
34
35	Text-to-Speech (TTS)
36
37	When user asks to "narrate", "read aloud", "say", or "create a voice-over":
38
39	```
40	Use MCP tool: text_to_speech
41	text: "<the text to narrate>"
42	voice_id: "JBFqnCBsd6RMkjVDRZzb" # Default: "George" (professional, neutral)
43	model_id: "eleven_multilingual_v2" # Use "eleven_turbo_v2_5" for low latency
44	```
45
46	Music Generation
47
48	When user asks to "compose", "create background music", or "make a soundtrack":
49
50	```
51	Use MCP tool: text_to_sound_effects (via cassetteai-music on fal.ai)
52	prompt: "<music description, e.g. 'upbeat lo-fi hip hop, 90 seconds'>"
53	duration_seconds: <duration>
54	```
55
56	Sound Effect (SFX)
57
58	When user asks for a specific sound (e.g., "a door creaking", "rain on a window"):
59
60	```
61	Use MCP tool: text_to_sound_effects
62	text: "<sound description>"
63	duration_seconds: <1-22>
64	```
65
66	Voice Cloning
67
68	When user provides an audio sample and wants to clone the voice:
69
70	```
71	Use MCP tool: voice_add
72	name: "<voice name>"
73	files: ["<audio_file_url>"]
74	```
75
76	---
77
78	## Example Conversations
79
80	User: "帮我把这段文字配音：欢迎来到我们的产品发布会"
81
82	```
83	→ Route to: text_to_speech
84	text: "欢迎来到我们的产品发布会"
85	voice_id: "JBFqnCBsd6RMkjVDRZzb"
86	model_id: "eleven_multilingual_v2"
87	```
88
89	> 🎙️ 配音完成！[点击收听](audio_url)
90
91	---
92
93	User: "给我生成一段 60 秒的轻松背景音乐，适合播客"
94
95	```
96	→ Route to: cassetteai-music (fal.ai)
97	prompt: "relaxing lo-fi background music for a podcast, gentle piano and soft beats, 60 seconds"
98	duration_seconds: 60
99	```
100
101	> 🎵 背景音乐生成完成！[点击收听](audio_url)
102
103	---
104
105	User: "生成一个科幻风格的门开启音效"
106
107	```
108	→ Route to: text_to_sound_effects
109	text: "a futuristic sci-fi door sliding open with a hydraulic hiss"
110	duration_seconds: 3
111	```
112
113	---
114
115	## Setup
116
117	### Required
118
119	Set `ELEVENLABS_API_KEY` in `~/.openclaw/openclaw.json`:
120
121	```json
122	{
123	"skills": {
124	"entries": {
125	"audiomind": {
126	"enabled": true,
127	"env": {
128	"ELEVENLABS_API_KEY": "your_elevenlabs_key_here"
129	}
130	}
131	}
132	}
133	}
134	```
135
136	Get your key at [elevenlabs.io/app/settings/api-keys](https://elevenlabs.io/app/settings/api-keys).
137
138	### Optional (for fal.ai music & SFX models)
139
140	```json
141	"FAL_KEY": "your_fal_key_here"
142	```
143
144	Get your key at [fal.ai/dashboard/keys](https://fal.ai/dashboard/keys).
145
146	---
147
148	## Self-Hosting the Proxy
149
150	The `cli.js` connects to a hosted proxy by default. If you want full control — or need to serve users in regions where `vercel.app` is blocked — you can deploy your own instance from the `proxy/` directory.
151
152	### Quick Deploy (Vercel)
153
154	```bash
155	cd proxy
156	npm install
157	vercel --prod
158	```
159
160	### Environment Variables
161
162	Set these in your Vercel project (Dashboard → Settings → Environment Variables):
163
164	\| Variable \| Required For \| Where to Get \|
165	\|---\|---\|---\|
166	\| `ELEVENLABS_API_KEY` \| TTS, SFX, Voice Clone \| [elevenlabs.io/app/settings/api-keys](https://elevenlabs.io/app/settings/api-keys) \|
167	\| `FAL_KEY` \| Music generation \| [fal.ai/dashboard/keys](https://fal.ai/dashboard/keys) \|
168	\| `VALID_PRO_KEYS` \| (Optional) Restrict access \| Comma-separated list of allowed client keys \|
169
170	### Point cli.js to Your Proxy
171
172	```bash
173	export AUDIOMIND_PROXY_URL="https://your-domain.com/api/audio"
174	```
175
176	Or set it in `~/.openclaw/openclaw.json`:
177
178	```json
179	{
180	"skills": {
181	"entries": {
182	"audiomind": {
183	"env": {
184	"AUDIOMIND_PROXY_URL": "https://your-doma

People who liked this also viewed

6 picks

Type