Skip to content
1337skills 1337skills

ElevenLabs Commands

Comprehensive ElevenLabs AI voice synthesis commands and workflows for text-to-speech and voice generation.

API Authentication

CommandDescription
curl -H "xi-api-key: <api-key>" <endpoint>API authentication
export ELEVEN_API_KEY=<key>Set environment variable
elevenlabs auth loginLogin to account
elevenlabs auth logoutLogout from account
elevenlabs auth statusCheck authentication status

Text-to-Speech API

EndpointDescription
POST /v1/text-to-speech/{voice_id}Generate speech
POST /v1/text-to-speech/{voice_id}/streamStream speech
GET /v1/voicesList available voices
GET /v1/voices/{voice_id}Get voice details
POST /v1/voices/addAdd custom voice

Voice Management

CommandDescription
GET /v1/voicesList all voices
GET /v1/voices/{voice_id}Get voice information
DELETE /v1/voices/{voice_id}Delete custom voice
POST /v1/voices/{voice_id}/editEdit voice settings
GET /v1/voices/settingsGet voice settings

Speech Generation

CommandDescription
curl -X POST "https://api.elevenlabs.io/v1/text-to-speech/21m00Tcm4TlvDq8ikWAM" -H "xi-api-key: <key>" -H "Content-Type: application/json" -d '{"text": "Hello world"}'Basic speech generation
curl -X POST "https://api.elevenlabs.io/v1/text-to-speech/21m00Tcm4TlvDq8ikWAM/stream" -H "xi-api-key: <key>"Streaming speech

Python SDK

CommandDescription
pip install elevenlabsInstall Python SDK
from elevenlabs import generate, playImport SDK
generate(text="Hello", voice="Bella")Generate speech
play(audio)Play generated audio
save(audio, "output.mp3")Save audio file

Voice Cloning

CommandDescription
POST /v1/voices/addClone voice from samples
POST /v1/voices/{voice_id}/samplesAdd voice samples
DELETE /v1/voices/{voice_id}/samples/{sample_id}Delete voice sample
GET /v1/voices/{voice_id}/samplesList voice samples

Voice Settings

ParameterDescription
stabilityVoice consistency (0.0-1.0)
similarity_boostVoice similarity (0.0-1.0)
styleSpeaking style (0.0-1.0)
use_speaker_boostEnhance speaker similarity

Audio Formats

FormatDescription
mp3_44100_128MP3 44.1kHz 128kbps
mp3_22050_32MP3 22.05kHz 32kbps
pcm_16000PCM 16kHz
pcm_22050PCM 22.05kHz
pcm_24000PCM 24kHz
pcm_44100PCM 44.1kHz

Pre-built Voices

Voice IDNameDescription
21m00Tcm4TlvDq8ikWAMRachelAmerican female
AZnzlk1XvdvUeBnXmlldDomiAmerican female
EXAVITQu4vr4xnSDxMaLBellaAmerican female
ErXwobaYiN019PkySvjVAntoniAmerican male
MF3mGyEYCl7XYWbV9V6OElliAmerican female
TxGEqnHWrfWFTfGW9XjXJoshAmerican male
VR6AewLTigWG4xSOukaGArnoldAmerican male
pNInz6obpgDQGcFmaJgBAdamAmerican male

Node.js SDK

CommandDescription
npm install elevenlabsInstall Node.js SDK
const { ElevenLabsAPI } = require('elevenlabs')Import SDK
const client = new ElevenLabsAPI({ apiKey: 'key' })Initialize client
client.textToSpeech.generate()Generate speech

Streaming Audio

CommandDescription
POST /v1/text-to-speech/{voice_id}/streamStream audio
curl -X POST -H "xi-api-key: <key>" --data-raw '{"text":"Hello"}' --output audio.mp3Stream to file

Voice Lab Features

FeatureDescription
Voice DesignCreate synthetic voices
Voice CloningClone existing voices
Professional CloningHigh-quality voice cloning
Voice LibraryBrowse voice collection

API Rate Limits

PlanCharacters/MonthConcurrent Requests
Free10,0002
Starter30,0003
Creator100,0005
Pro500,00010
Scale2,000,00025

Error Handling

Error CodeDescription
400Bad Request
401Unauthorized
403Forbidden
404Not Found
422Unprocessable Entity
429Too Many Requests
500Internal Server Error

Advanced Parameters

ParameterDescription
model_idTTS model to use
voice_settingsVoice configuration
pronunciation_dictionary_locatorsCustom pronunciations
seedReproducible generation

Webhook Configuration

CommandDescription
POST /v1/webhooksCreate webhook
GET /v1/webhooksList webhooks
DELETE /v1/webhooks/{webhook_id}Delete webhook
PUT /v1/webhooks/{webhook_id}Update webhook

Projects and Dubbing

CommandDescription
POST /v1/projectsCreate project
GET /v1/projectsList projects
POST /v1/dubbingCreate dubbing project
GET /v1/dubbing/{dubbing_id}Get dubbing status

Usage Analytics

CommandDescription
GET /v1/user/subscriptionGet subscription info
GET /v1/userGet user information
GET /v1/usage/character-statsGet usage statistics

CLI Tool

CommandDescription
elevenlabs --helpShow help
elevenlabs tts --text "Hello" --voice RachelGenerate speech
elevenlabs voices listList voices
elevenlabs voices clone --name "MyVoice"Clone voice

Python Examples

CodeDescription
audio = generate(text="Hello", voice="Bella", model="eleven_monolingual_v1")Basic generation
play(audio)Play audio
save(audio, "hello.mp3")Save to file

JavaScript Examples

CodeDescription
const audio = await elevenlabs.generate({ text: "Hello", voice: "Rachel" })Generate audio
fs.writeFileSync("audio.mp3", audio)Save to file

Voice Cloning Process

StepDescription
1. Upload samplesProvide voice samples
2. Train modelAI learns voice patterns
3. Test generationVerify voice quality
4. Fine-tune settingsAdjust parameters
5. Deploy voiceUse in production

Best Practices

PracticeDescription
Clear audio samplesHigh-quality recordings
Diverse samplesVarious emotions/styles
Consistent speakerSame person throughout
Proper length1-5 minutes total
Good microphoneProfessional recording

Integration Examples

PlatformIntegration
Discord BotVoice message generation
PodcastAutomated narration
E-learningCourse voice-overs
GamingCharacter voices
AccessibilityText-to-speech for visually impaired

Troubleshooting

IssueSolution
Poor voice qualityImprove sample quality
Rate limit exceededUpgrade plan or wait
Authentication failedCheck API key
Voice not foundVerify voice ID
Audio distortionAdjust voice settings

Environment Variables

VariableDescription
ELEVEN_API_KEYAPI authentication key
ELEVEN_API_URLAPI base URL
ELEVEN_TIMEOUTRequest timeout

Configuration Files

FileDescription
.elevenlabs.jsonConfiguration file
voices.jsonVoice definitions
settings.jsonDefault settings

Monitoring and Analytics

MetricDescription
Characters usedMonthly usage
API callsRequest count
Voice generationsAudio created
Error rateFailed requests