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, and more)
npx skills add inference-sh/skills@text-to-speech
# Full platform skill (all 250+ 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---56# ElevenLabs Text-to-Speech78Premium text-to-speech with 22+ voices via [inference.sh](https://inference.sh) CLI.9101112## Quick Start1314> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md)1516```bash17belt login1819# Generate speech with ElevenLabs20belt app run elevenlabs/tts --input '{"text": "Hello, welcome to our product demo.", "voice": "aria"}'21```222324## Available Models2526| Model | ID | Best For | Latency |27|-------|----|----------|---------|28| Multilingual v2 | `eleven_multilingual_v2` | Highest quality, 32 languages | ~250ms |29| Turbo v2.5 | `eleven_turbo_v2_5` | Balance of speed & quality | ~150ms |30| Flash v2.5 | `eleven_flash_v2_5` | Ultra-low latency | ~75ms |3132## Voice Library3334### Female Voices3536| Voice | Style |37|-------|-------|38| `aria` | American, conversational |39| `alice` | British, confident |40| `bella` | American, warm |41| `jessica` | American, expressive |42| `laura` | American, professional |43| `lily` | British, soft |44| `sarah` | American, friendly |4546### Male Voices4748| Voice | Style |49|-------|-------|50| `george` | British, authoritative |51| `adam` | American, deep |52| `bill` | American, mature |53| `brian` | American, conversational |54| `callum` | Transatlantic, intense |55| `charlie` | Australian, natural |56| `chris` | American, casual |57| `daniel` | British, commanding |58| `eric` | American, friendly |59| `harry` | American, young |60| `liam` | American, articulate |61| `matilda` | American, warm |62| `river` | American, confident |63| `roger` | American, authoritative |64| `will` | American, bright |6566## Examples6768### Basic Speech6970```bash71belt app run elevenlabs/tts --input '{"text": "Welcome to our quarterly earnings presentation.", "voice": "george"}'72```7374### Choose a Model7576```bash77# Highest quality78belt app run elevenlabs/tts --input '{79 "text": "This is our premium multilingual model with the best quality.",80 "voice": "aria",81 "model": "eleven_multilingual_v2"82}'8384# Ultra-fast for real-time applications85belt app run elevenlabs/tts --input '{86 "text": "Flash model for low-latency applications.",87 "voice": "brian",88 "model": "eleven_flash_v2_5"89}'90```9192### Voice Tuning9394```bash95belt app run elevenlabs/tts --input '{96 "text": "Fine-tune the voice characteristics for your use case.",97 "voice": "bella",98 "stability": 0.3,99 "similarity_boost": 0.9,100 "style": 0.4101}'102```103104| Parameter | Range | Effect |105|-----------|-------|--------|106| `stability` | 0-1 | Higher = more consistent, lower = more expressive |107| `similarity_boost` | 0-1 | Higher = closer to original voice character |108| `style` | 0-1 | Higher = more style exaggeration |109| `use_speaker_boost` | true/false | Enhances speaker clarity |110111### Output Formats112113```bash114# High-quality MP3115belt app run elevenlabs/tts --input '{116 "text": "High quality audio output.",117 "voice": "daniel",118 "output_format": "mp3_44100_192"119}'120```121122| Format | Description |123|--------|-------------|124| `mp3_44100_128` | MP3 at 44.1kHz, 128kbps (default) |125| `mp3_44100_192` | MP3 at 44.1kHz, 192kbps |126| `pcm_16000` | Raw PCM at 16kHz |127| `pcm_22050` | Raw PCM at 22.05kHz |128| `pcm_24000` | Raw PCM at 24kHz |129| `pcm_44100` | Raw PCM at 44.1kHz |130131### Multilingual132133ElevenLabs supports 32 languages including English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Hindi, Russian, and more.134135```bash136# Spanish137belt app run elevenlabs/tts --input '{138 "text": "Hola, bienvenidos a nuestra presentación.",139 "voice": "aria",140 "model": "eleven_multilingual_v2"141}'142143# French144belt app run elevenlabs/tts --input '{145 "text": "Bonjour, bienvenue à notre démonstration.",146 "voice": "alice",147 "model": "eleven_multilingual_v2"148}'149```150151## Voice + Video Workflow152153```bash154# 1. Generate voiceover155belt app run elevenlabs/tts --input '{156 "text": "Introducing the future of AI-powered content creation.",157 "voice": "george"158}' > voiceover.json159160# 2. Create talking head video161belt app run bytedance/omnihuman-1-5 --input '{162 "image_url": "https://portrait.jpg",163 "audio_url": "<audio-url-from-step-1>"164}'165```166167## Use Cases168169- **Voiceovers**: Product demos, explainer videos, commercials170- **Audiobooks**: Long-form narration with consistent voices171- **Podcasts**: AI hosts with natural delivery172- **E-learning**: Course narration in multiple languages173- **Accessibility**: High-quality screen reader content174- **IVR**: Professional phone system messages175- **Video Narration**: Documentary and social media content176177## Related Skills178179```bash180# ElevenLabs multi-speaker dialogue181npx skills add inference-sh/skills@elevenlabs-dialogue182183# ElevenLabs voice changer184npx skills add inference-sh/skills@elevenlabs-voice-changer185186# ElevenLabs sound effects187npx skills add inference-sh/skills@elevenlabs-sound-effects188189# All TTS models (Kokoro, DIA, Chatterbox, and more)190npx skills add inference-sh/skills@text-to-speech191192# Full platform skill (all 250+ apps)193npx skills add inference-sh/skills@infsh-cli194```195196Browse all audio apps: `belt app list --category audio`
midudev