The Autohive ElevenLabs integration connects your ElevenLabs account with Autohive’s automation platform, enabling:

  • Text-to-speech conversion - Transform written content into lifelike speech with AI-powered voice generation
  • Voice discovery - Browse and filter available voices by category, use case, and characteristics
  • Audio management - Access generation history, download previously created audio files, and track usage
  • Subscription monitoring - Check character quotas, credit limits, and usage statistics for account planning
  • Voice customization - Control voice settings including stability, similarity, style, and speaker boost
  • Multi-format support - Generate audio in various formats including MP3 and PCM for different use cases
  • Professional voices - Access 20 premade professional voices with multiple accents and characteristics

Install the integration

  1. Get your ElevenLabs API key:

    • Log in to your ElevenLabs account at https://elevenlabs.io
    • Navigate to Settings > Developers > API Keys
    • Click “Create API Key” and give it a name
    • Copy the API key immediately (shown only once)

  2. Log in to Autohive and navigate to Your user profile > Connections or Your workspace -> Manage workspace

  3. Locate the ElevenLabs Integration card and click Connect

    List of integrations in Autohive

  4. Enter your API key in the authentication field

  5. Confirm installation - your ElevenLabs account will be connected to Autohive

Use the integration

You can now use the integration with your agents, workflows and scheduled tasks!

  1. Follow our Create your first agent guide on how to create an agent.
  2. In the ‘Agent settings’, scroll down to the ‘Add capabilities’ section and turn on the ElevenLabs capability. You can choose what individual ElevenLabs capabilities to turn on and off.
  3. Once the settings have been selected, begin prompting the agent of the workflow you’d like to achieve with Autohive and ElevenLabs!

Available capabilities

Voice Generation

  • Text to Speech: Convert text to realistic speech using AI-powered voice models with customizable settings
  • Model Selection: Choose from multiple AI models including multilingual and Turbo variants for optimal quality and speed
  • Output Format Control: Generate audio in various formats (MP3, PCM) with different quality and sample rate options
  • Voice Settings Customization: Fine-tune stability, similarity boost, style, and speaker enhancement parameters

Voice Management

  • List Voices: Browse all available voices with filtering by category, use cases, and search terms
  • Get Voice Details: Retrieve comprehensive voice metadata including labels, samples, and characteristics
  • Get Voice Settings: Access voice configuration parameters for stability, similarity, and style settings
  • Voice Discovery: Search and filter voices by category (premade, cloned, generated, professional) and use cases

Audio History

  • List History: Access all previously generated audio items with filtering and pagination support
  • Download History Audio: Retrieve previously generated audio files without using additional credits
  • History Tracking: Monitor generation history including text content, voice used, and timestamps
  • Usage Management: Track credit consumption and generation patterns for account optimization

Account Management

  • Get User Subscription: View subscription tier, character quota, character limit, and credit usage statistics
  • Usage Monitoring: Track character consumption and remaining credits for billing and planning
  • Account Information: Access subscription details including voice limits and feature availability

Key features

AI-Powered Voice Generation

  • Realistic text-to-speech with natural-sounding voices and human-like intonation
  • Multiple AI models supporting different languages and voice characteristics
  • Character-based pricing with transparent credit consumption tracking
  • Support for both standard and Turbo models for quality and speed optimization

Comprehensive Voice Library

  • 20 premade professional voices included in free tier with various accents and characteristics
  • Voice filtering and search capabilities for efficient voice discovery
  • Voice categories including premade, cloned, generated, and professional options
  • Voice metadata and samples for informed voice selection

Flexible Audio Output

  • Multiple output formats supporting MP3 and PCM with various quality settings
  • Base64-encoded audio files for easy integration with workflows and storage
  • Sample rate options including 16kHz, 22.05kHz, and 44.1kHz for different use cases
  • Configurable bitrates and quality settings for optimal file size and audio quality

Credit-Efficient History Management

  • Free access to generation history without additional credit consumption
  • Re-download previously generated audio files at no cost
  • History filtering by voice ID for organized audio asset management
  • Pagination support for large generation histories

Common use cases

Content Creation and Publishing

  • Convert blog posts and articles into audio versions for accessibility and reach
  • Generate podcast intros, outros, and episode narration with consistent voice branding
  • Create audiobook narration from written manuscripts and content
  • Produce video voiceovers and explainer video narration automatically

Marketing and Communication

  • Generate voice content for marketing campaigns and promotional materials
  • Create multilingual audio content for global audience engagement
  • Produce branded audio signatures and company announcements
  • Generate personalized audio messages for customer communication

E-Learning and Training

  • Convert educational content and course materials into audio format
  • Create training module narration and instructional videos
  • Generate language learning materials with native speaker voices
  • Produce accessible learning content for diverse student needs

Automated Audio Production

  • Generate voice notifications and alerts from text triggers and events
  • Create dynamic audio content based on data and workflow inputs
  • Batch convert documents and text content into speech automatically
  • Produce scheduled audio reports and summaries from business data

Voice Experimentation and Testing

  • Test different voices and settings for content optimization
  • Compare voice characteristics and find optimal voice for brand identity
  • Experiment with voice parameters for specific emotional tones
  • Generate audio samples for client approval and feedback

Audio generation settings

Voice Settings Parameters

  • Stability: Controls consistency (0.0-1.0) - Higher values produce more consistent speech patterns
  • Similarity Boost: Voice similarity to original (0.0-1.0) - Affects voice character preservation
  • Style: Expressive style exaggeration (0.0-1.0) - Controls emotional expression and variation
  • Speaker Boost: Enable speaker enhancement - Improves clarity and vocal characteristics

Output Format Options

  • MP3 Formats: mp3_44100_128, mp3_44100_64, mp3_22050_32 for compressed audio with quality options
  • PCM Formats: pcm_16000, pcm_22050, pcm_24000, pcm_44100 for uncompressed high-quality audio
  • Format Selection: Choose based on use case - MP3 for web/streaming, PCM for professional editing

Model Selection

  • Multilingual Models: Support for multiple languages with natural pronunciation
  • Turbo Models: Faster generation with reduced credit consumption (0.5 credits per character)
  • Standard Models: Higher quality with full expressiveness (1 credit per character)

Credit usage and billing

Free Tier Allocation

  • 10,000 characters per month included at no cost
  • Approximately 2-3 minutes of generated audio content
  • Non-commercial use only with attribution requirements
  • 20 premade professional voices accessible for all generations

Credit Consumption

  • Standard models: 1 credit per character of text input
  • Turbo models: 0.5 credits per character (2x more efficient)
  • Free actions: Listing voices, accessing history, downloading previous audio (0 credits)
  • Generation limits: 2,500 characters maximum per request on free tier

Cost Optimization

  • Re-download previously generated audio from history at no additional cost
  • Use Turbo models for draft content and high-volume generation
  • Batch similar content to minimize repeated generation costs
  • Monitor subscription usage with get_user_subscription action

Voice categories and types

Premade Voices

  • 20 professional voices included in free tier with curated characteristics
  • Multiple accents including American, British, Australian, and international options
  • Various voice characteristics including age, gender, and tone profiles
  • Optimized for different content types and use cases

Voice Characteristics

  • Gender variations for appropriate content matching
  • Age profiles from young adult to mature voices
  • Accent diversity for regional and international content
  • Tone options from professional to conversational styles

Use Case Optimization

  • Filter voices by intended use case (narration, audiobooks, conversational, etc.)
  • Category-based filtering for efficient voice discovery
  • Search functionality for finding specific voice characteristics
  • Voice samples available for preview and testing

API integration details

Authentication

  • API key-based authentication using custom xi-api-key header
  • Secure token storage and transmission with encrypted key management
  • Long-lived API keys without automatic expiration
  • Single key access across all ElevenLabs API endpoints

Data Format

  • Base64-encoded audio file outputs for universal compatibility
  • JSON response format for consistent data structure
  • Support for multiple audio encoding formats and sample rates
  • Comprehensive error handling with detailed error messages

Rate Limits

  • Free tier: 10,000 characters per month with daily distribution
  • Character quota resets monthly on subscription anniversary
  • API rate limiting handled automatically by ElevenLabs
  • Usage monitoring through subscription endpoint for quota tracking

Disconnect the integration

Important: Disconnecting stops API access but preserves existing data in both systems.

  1. Navigate to Your user profile -> Connections or Your workspace -> Manage workspace
  2. Find the ElevenLabs Integration
  3. Click Disconnect and confirm

Data Impact: Existing data remains unchanged in both systems, but sync stops and Autohive loses ElevenLabs API access.

Remove access

From ElevenLabs: Go to your ElevenLabs Settings > API Keys > Delete the API key to revoke access for all connected applications