Install the belt CLI skill: npx skills add belt-sh/cli
ElevenLabs Text-to-Speech
Premium text-to-speech with 22+ voices via inference.sh CLI.
Quick Start
Requires inference.sh CLI (belt). Install instructions
belt login
# Generate speech with ElevenLabs
belt app run elevenlabs/tts --input '{"text": "Hello, welcome to our product demo.", "voice": "aria"}'
Available Models
| Model |
ID |
Best For |
Latency |
| Multilingual v2 |
eleven_multilingual_v2 |
Highest quality, 32 languages |
~250ms |
| Turbo v2.5 |
eleven_turbo_v2_5 |
Balance of speed & quality |
~150ms |
| Flash v2.5 |
eleven_flash_v2_5 |
Ultra-low latency |
~75ms |
Voice Library
Female Voices
| Voice |
Style |
aria |
American, conversational |
alice |
British, confident |
bella |
American, warm |
jessica |
American, expressive |
laura |
American, professional |
lily |
British, soft |
sarah |
American, friendly |
Male Voices
| Voice |
Style |
george |
British, authoritative |
adam |
American, deep |
bill |
American, mature |
brian |
American, conversational |
callum |
Transatlantic, intense |
charlie |
Australian, natural |
chris |
American, casual |
daniel |
British, commanding |
eric |
American, friendly |
harry |
American, young |
liam |
American, articulate |
matilda |
American, warm |
river |
American, confident |
roger |
American, authoritative |
will |
American, bright |
Examples
Basic Speech
belt app run elevenlabs/tts --input '{"text": "Welcome to our quarterly earnings presentation.", "voice": "george"}'
Choose a Model
# Highest quality
belt app run elevenlabs/tts --input '{
"text": "This is our premium multilingual model with the best quality.",
"voice": "aria",
"model": "eleven_multilingual_v2"
}'
# Ultra-fast for real-time applications
belt app run elevenlabs/tts --input '{
"text": "Flash model for low-latency applications.",
"voice": "brian",
"model": "eleven_flash_v2_5"
}'
Voice Tuning
belt app run elevenlabs/tts --input '{
"text": "Fine-tune the voice characteristics for your use case.",
"voice": "bella",
"stability": 0.3,
"similarity_boost": 0.9,
"style": 0.4
}'
| Parameter |
Range |
Effect |
stability |
0-1 |
Higher = more consistent, lower = more expressive |
similarity_boost |
0-1 |
Higher = closer to original voice character |
style |
0-1 |
Higher = more style exaggeration |
use_speaker_boost |
true/false |
Enhances speaker clarity |
Output Formats
# High-quality MP3
belt app run elevenlabs/tts --input '{
"text": "High quality audio output.",
"voice": "daniel",
"output_format": "mp3_44100_192"
}'
| Format |
Description |
mp3_44100_128 |
MP3 at 44.1kHz, 128kbps (default) |
mp3_44100_192 |
MP3 at 44.1kHz, 192kbps |
pcm_16000 |
Raw PCM at 16kHz |
pcm_22050 |
Raw PCM at 22.05kHz |
pcm_24000 |
Raw PCM at 24kHz |
pcm_44100 |
Raw PCM at 44.1kHz |
Multilingual
ElevenLabs supports 32 languages including English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Hindi, Russian, and more.
# Spanish
belt app run elevenlabs/tts --input '{
"text": "Hola, bienvenidos a nuestra presentación.",
"voice": "aria",
"model": "eleven_multilingual_v2"
}'
# French
belt app run elevenlabs/tts --input '{
"text": "Bonjour, bienvenue à notre démonstration.",
"voice": "alice",
"model": "eleven_multilingual_v2"
}'
Voice + Video Workflow
# 1. Generate voiceover
belt app run elevenlabs/tts --input '{
"text": "Introducing the future of AI-powered content creation.",
"voice": "george"
}' > voiceover.json
# 2. Create talking head video
belt app run bytedance/omnihuman-1-5 --input '{
"image_url": "https://portrait.jpg",
"audio_url": "<audio-url-from-step-1>"
}'
Use Cases
- Voiceovers: Product demos, explainer videos, commercials
- Audiobooks: Long-form narration with consistent voices
- Podcasts: AI hosts with natural delivery
- E-learning: Course narration in multiple languages
- Accessibility: High-quality screen reader content
- IVR: Professional phone system messages
- Video Narration: Documentary and social media content
Related Skills
# ElevenLabs multi-speaker dialogue
npx skills add inference-sh/skills@elevenlabs-dialogue
# ElevenLabs voice changer
npx skills add inference-sh/skills@elevenlabs-voice-changer
# ElevenLabs sound effects
npx skills add inference-sh/skills@elevenlabs-sound-effects
# All TTS models (Kokoro, DIA, Chatterbox, Inworld TTS, and more)
npx skills add inference-sh/skills@text-to-speech
# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli
Browse all audio apps: belt app list --category audio
1---2name: elevenlabs-tts3description: ElevenLabs text-to-speech with 22+ premium voices, multilingual support, and voice tuning via inference.sh CLI. Models: eleven_multilingual_v2 (highest quality), eleven_turbo_v2_5 (low latency), eleven_flash_v2_5 (ultra-fast). Capabilities: text-to-speech, voice selection, stability/style control, 32 languages. Use for: voiceovers, audiobooks, video narration, podcasts, accessibility, IVR. Triggers: elevenlabs, eleven labs, elevenlabs tts, premium tts, professional voice, ai voice, high quality tts, multilingual tts, eleven labs voice, voice generation, natural speech, realistic voice, voice over, speech synthesis4---5
6> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
7
8# ElevenLabs Text-to-Speech
9
10Premium text-to-speech with 22+ voices via [inference.sh](https://inference.sh) CLI.
11
12
13
14## Quick Start
15
16> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md)
17
18```bash
19belt login
20
21# Generate speech with ElevenLabs
22belt app run elevenlabs/tts --input '{"text": "Hello, welcome to our product demo.", "voice": "aria"}'
23```
24
25
26## Available Models
27
28| Model | ID | Best For | Latency |
29|-------|----|----------|---------|
30| Multilingual v2 | `eleven_multilingual_v2` | Highest quality, 32 languages | ~250ms |
31| Turbo v2.5 | `eleven_turbo_v2_5` | Balance of speed & quality | ~150ms |
32| Flash v2.5 | `eleven_flash_v2_5` | Ultra-low latency | ~75ms |
33
34## Voice Library
35
36### Female Voices
37
38| Voice | Style |
39|-------|-------|
40| `aria` | American, conversational |
41| `alice` | British, confident |
42| `bella` | American, warm |
43| `jessica` | American, expressive |
44| `laura` | American, professional |
45| `lily` | British, soft |
46| `sarah` | American, friendly |
47
48### Male Voices
49
50| Voice | Style |
51|-------|-------|
52| `george` | British, authoritative |
53| `adam` | American, deep |
54| `bill` | American, mature |
55| `brian` | American, conversational |
56| `callum` | Transatlantic, intense |
57| `charlie` | Australian, natural |
58| `chris` | American, casual |
59| `daniel` | British, commanding |
60| `eric` | American, friendly |
61| `harry` | American, young |
62| `liam` | American, articulate |
63| `matilda` | American, warm |
64| `river` | American, confident |
65| `roger` | American, authoritative |
66| `will` | American, bright |
67
68## Examples
69
70### Basic Speech
71
72```bash
73belt app run elevenlabs/tts --input '{"text": "Welcome to our quarterly earnings presentation.", "voice": "george"}'
74```
75
76### Choose a Model
77
78```bash
79# Highest quality
80belt app run elevenlabs/tts --input '{
81 "text": "This is our premium multilingual model with the best quality.",
82 "voice": "aria",
83 "model": "eleven_multilingual_v2"
84}'
85
86# Ultra-fast for real-time applications
87belt app run elevenlabs/tts --input '{
88 "text": "Flash model for low-latency applications.",
89 "voice": "brian",
90 "model": "eleven_flash_v2_5"
91}'
92```
93
94### Voice Tuning
95
96```bash
97belt app run elevenlabs/tts --input '{
98 "text": "Fine-tune the voice characteristics for your use case.",
99 "voice": "bella",
100 "stability": 0.3,
101 "similarity_boost": 0.9,
102 "style": 0.4
103}'
104```
105
106| Parameter | Range | Effect |
107|-----------|-------|--------|
108| `stability` | 0-1 | Higher = more consistent, lower = more expressive |
109| `similarity_boost` | 0-1 | Higher = closer to original voice character |
110| `style` | 0-1 | Higher = more style exaggeration |
111| `use_speaker_boost` | true/false | Enhances speaker clarity |
112
113### Output Formats
114
115```bash
116# High-quality MP3
117belt app run elevenlabs/tts --input '{
118 "text": "High quality audio output.",
119 "voice": "daniel",
120 "output_format": "mp3_44100_192"
121}'
122```
123
124| Format | Description |
125|--------|-------------|
126| `mp3_44100_128` | MP3 at 44.1kHz, 128kbps (default) |
127| `mp3_44100_192` | MP3 at 44.1kHz, 192kbps |
128| `pcm_16000` | Raw PCM at 16kHz |
129| `pcm_22050` | Raw PCM at 22.05kHz |
130| `pcm_24000` | Raw PCM at 24kHz |
131| `pcm_44100` | Raw PCM at 44.1kHz |
132
133### Multilingual
134
135ElevenLabs supports 32 languages including English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Hindi, Russian, and more.
136
137```bash
138# Spanish
139belt app run elevenlabs/tts --input '{
140 "text": "Hola, bienvenidos a nuestra presentación.",
141 "voice": "aria",
142 "model": "eleven_multilingual_v2"
143}'
144
145# French
146belt app run elevenlabs/tts --input '{
147 "text": "Bonjour, bienvenue à notre démonstration.",
148 "voice": "alice",
149 "model": "eleven_multilingual_v2"
150}'
151```
152
153## Voice + Video Workflow
154
155```bash
156# 1. Generate voiceover
157belt app run elevenlabs/tts --input '{
158 "text": "Introducing the future of AI-powered content creation.",
159 "voice": "george"
160}' > voiceover.json
161
162# 2. Create talking head video
163belt app run bytedance/omnihuman-1-5 --input '{
164 "image_url": "https://portrait.jpg",
165 "audio_url": "<audio-url-from-step-1>"
166}'
167```
168
169## Use Cases
170
171- **Voiceovers**: Product demos, explainer videos, commercials
172- **Audiobooks**: Long-form narration with consistent voices
173- **Podcasts**: AI hosts with natural delivery
174- **E-learning**: Course narration in multiple languages
175- **Accessibility**: High-quality screen reader content
176- **IVR**: Professional phone system messages
177- **Video Narration**: Documentary and social media content
178
179## Related Skills
180
181```bash
182# ElevenLabs multi-speaker dialogue
183npx skills add inference-sh/skills@elevenlabs-dialogue
184
185# ElevenLabs voice changer
186npx skills add inference-sh/skills@elevenlabs-voice-changer
187
188# ElevenLabs sound effects
189npx skills add inference-sh/skills@elevenlabs-sound-effects
190
191# All TTS models (Kokoro, DIA, Chatterbox, Inworld TTS, and more)
192npx skills add inference-sh/skills@text-to-speech
193
194# Full platform skill (all apps)
195npx skills add inference-sh/skills@infsh-cli
196```
197
198Browse all audio apps: `belt app list --category audio`
101-skills