Workspaces
- Service account API key management: Added comprehensive API endpoints for managing service account API keys, including creation, retrieval, updating, and deletion capabilities. See Service Accounts documentation.
Conversational AI
- Post-call webhook migration: The post call webhook format is being migrated so that webhook handlers can be auto generated in the SDKs. This is not a breaking change, and no further action is required if your current handler accepts additional fields. Please see more information here.
- Agent transfer improvements: Fixed system variable
system_agent_id
to properly update after agent-to-agent transfers, ensuring accurate conversation context tracking. Added newsystem_current_agent_id
variable for tracking current active agent. Learn more about dynamic variables. - Enhanced public agent page: Added text input functionality and dynamic variable support to the public talk-to-agent page. You can now pass dynamic variables via URL parameters (e.g.,
?var_username=value
) and use text input during voice conversations. See dynamic variables guide. - Voicemail detection: Added voicemail detection as a built-in tool for conversational AI agents to improve call handling. Learn about voicemail detection.
- Conversation filtering: Added
user_id
query parameter to conversation list endpoint for filtering conversations by initiating user.
Speech to Text
- Multi-channel transcription: Added
use_multi_channel
parameter to transcription endpoint for processing audio files with multiple speakers on separate channels. Supports up to 5 channels with per-channel transcription results. See multichannel guide.
Studio
- Caption support: Added caption functionality to Studio projects with new
captions_enabled
andcaption_style
properties for both podcasts and general projects. Learn more about Studio.
SDKs
- JavaScript SDK v2.7.0: Released with latest API support and improvements
- Python SDK v2.8.1: Released with latest API support and improvements
- @elevenlabs/client v0.4.1: Updated client library with latest features, including WebRTC support
- @elevenlabs/react v0.4.1: Enhanced React components with latest features, including WebRTC support
- @elevenlabs/react-native v0.1.1: New React Native package for mobile integration with ElevenLabs Conversational AI, based on WebRTC
- @elevenlabs/convai-widget-embed v0.1.0: New package for embedding conversational AI widgets into web applications
- Swift SDK v2.0.3: Released with WebRTC support for real-time Conversational AI integration on Apple platforms
API Schema Updates
View API changes
New Endpoints
- Service Account Management: Added 5 new endpoints for service account API key management:
GET /v1/service-accounts/{service_account_user_id}/api-keys
- Retrieve service account API keysPOST /v1/service-accounts/{service_account_user_id}/api-keys
- Create service account API keyDELETE /v1/service-accounts/{service_account_user_id}/api-keys/{api_key_id}
- Delete service account API keyPATCH /v1/service-accounts/{service_account_user_id}/api-keys/{api_key_id}
- Update service account API keyGET /v1/service-accounts
- Get workspace service accounts
Removed Endpoints
- Legacy Project Endpoints: Removed 22 deprecated project management endpoints as part of Studio API consolidation:
- All
/v1/projects/*
endpoints (replaced by/v1/studio/projects/*
) - Legacy Text to Voice endpoints (
/v1/text-to-voice/create-voice-from-preview
,/v1/text-to-voice/remixing-sessions/*
) - Legacy ConvAI knowledge base endpoints
- All
Updated Endpoints
Speech to Text
- Multi-channel support: Updated
/v1/speech-to-text
endpoint:- Added
use_multi_channel
parameter for processing multi-speaker audio files - Modified response structure to include optional
language_code
,language_probability
,text
, andwords
properties
- Added
Conversational AI
- Enhanced agent configuration: Updated agent creation and management endpoints:
- Added voicemail detection to built-in tools
- Improved RAG configuration with
max_retrieved_rag_chunks_count
parameter - Enhanced conversation token endpoint with
source
andversion
parameters - Added
user_id
filtering to conversations list endpoint
Studio Projects
- Caption support: Updated Studio project endpoints to include:
captions_enabled
property for enabling/disabling captionscaption_style
property for global caption styling configuration
Text to Voice
- Improved voice generation: Enhanced voice creation endpoints with:
loudness
control (-1 to 1 range, 0 corresponds to -24 LUFS)quality
parameter for balancing output quality vs varietyguidance_scale
parameter for controlling AI creativity vs prompt adherence
Conversational AI
- Agent workspace overrides: Enhanced agent configuration with workspace-level overrides for better enterprise management and customization.
- Agent API improvements: Updated agent creation and modification endpoints with enhanced configuration options, though these changes may break backward compatibility.
Dubbing
- Dubbing endpoint access: Added new endpoint to list all available dubs.
API
View API changes
New Endpoints
- Added 1 new endpoints:
- List dubs you have access to -
GET /v1/dubbing
- List dubs you have access to -
Updated Endpoints
Text to Speech
- Updated Text to Speech endpoints with backward compatible changes:
- Convert text to speech - Enhanced response schema
- Convert with timestamps - Improved timestamp handling
- Stream text to speech - Enhanced streaming response
Voice Management
- Updated Voice endpoints with backward compatible improvements:
- Get voices - Enhanced voice information schema
- Get voice - Improved voice details response
- Get voice settings - Enhanced settings schema
Voice Creation
- Updated Voice Creation endpoints:
- Create voice previews - Enhanced preview creation
- Create voice from preview - Improved voice generation
- Create voice - Enhanced voice creation response
Dubbing
- Updated Dubbing endpoints with backward compatible changes:
- Dub a video or audio file - Enhanced dubbing request schema
- Get dubbing project - Improved project response
Workspace Management
- Breaking Change: Updated Workspace endpoints:
- Get workspace resource - Modified
resource_type
query parameter handling and response schema - Share workspace resource - Enhanced sharing configuration
- Unshare workspace resource - Improved unsharing workflow
- Get workspace resource - Modified
Speech to Text
- Updated Speech to Text endpoint:
- Convert speech to text - Enhanced transcription request and response schemas
Conversational AI
Updated Conversational AI endpoints with enhanced changes:
- Create agent - Modified agent creation schema with workspace overrides
- Get agent - Enhanced agent response with new configuration options
- Update agent - Improved agent update capabilities
- Simulate conversation - Enhanced conversation simulation
- Stream conversation simulation - Improved streaming simulation
Other Updates
- Get conversation - Enhanced conversation details
- Get Conversational AI settings - Improved settings response
- Update Conversational AI settings - Enhanced settings modification
Conversational AI
- Azure OpenAI custom LLM support: Added support for Azure-hosted OpenAI models in custom LLM configurations. When using an Azure endpoint, a new required field for API version is now available in the UI.
- Genesys output variables: Added support for output variables when using Genesys integrations, enabling better call analytics and data collection.
- Gemini 2.5 Preview Models Deprecation: Models
gemini-2.5-flash-preview-05-20
andgemini-2.5-flash-preview-04-17
have been deprecated in Conversational AI as they are being deprecated on 15th July by Google. All agents using these models will automatically be transferred togemini-2.5-flash
the next time they are used. No action is required. - WebRTC rollout: Began progressive rollout of WebRTC capabilities for improved connection stability and performance. WebRTC mode can be selected in the React SDK and is used in 11.ai.
- Keypad touch tone: Fixed an issue affecting playing keypad touch tones on Twilio. See keypad touch tone documentation.
Voices
- Language collection navigation: Added quick navigation from language preview collections to view all available voices in that language, making it easier to explore voice options by language.
Text to Voice
- Preview streaming: Added new streaming endpoint for Text to Voice previews, allowing real-time streaming of generated voice previews via
/v1/text-to-voice/{generated_voice_id}/stream
. - Enhanced voice design: Added
stream_previews
option to voice design endpoint, enabling streaming-only preview generation for improved performance. - Improved parameter controls: Enhanced
loudness
, quality, and guidance scale parameters with better control options for more precise voice generation.
Studio
- Podcast customization: Added support for intro and outro text in podcast creation, along with custom instructions prompts for better style and tone control.
SDKs
- JavaScript SDK v2.6.0: Released with latest API support and improvements
- Python SDK v2.7.1: Released with bug fixes and enhancements
- @elevenlabs/client v0.3.0: Updated client library with support for User IDs in Conversational AI.
- @elevenlabs/react v0.3.0: Add WebRTC debug support.
API
View API changes
New Endpoints
- Added 1 new endpoint:
- Stream Text to Voice Preview - Stream generated voice previews in real-time
Updated Endpoints
Text to Voice
- Create voice previews - Enhanced
loudness
,quality
, andguidance_scale
parameter descriptions - Design voice - Added
stream_previews
property for streaming-only preview generation
Studio
- Create podcast - Added
intro
,outro
, andinstructions_prompt
properties
Conversational AI
- Simulate conversation - Enhanced simulation configuration with improved parameter descriptions
- Stream simulate conversation - Enhanced simulation configuration with improved parameter descriptions
- Get conversational AI settings - Updated RAG retention period configuration
- Update conversational AI settings - Updated RAG retention period configuration
- Retry batch calling - Added batch retry functionality
Conversational AI
-
HIPAA Compliance: Gemini 2.5 Flash is now available for HIPAA customers, providing enhanced AI capabilities while maintaining strict healthcare compliance standards.
-
Post-call Audio: Added support for returning call audio in post-call webhooks, enabling comprehensive conversation analysis and quality assurance workflows.
-
Enhanced Widget: Added additional text customization options including start chat button text, chatting status text, and input placeholders for text-only and new conversations.
-
Agent Transfers: Improved agent transfer capabilities with transfer delay configuration, custom transfer messages, and control over transferred agent first message behavior.
-
SIP Trunk Enhancements: Added support for separate inbound and outbound SIP trunk configurations with enhanced access control and transfer options.
Dubbing
-
API Schema Update: Updated our API documentation to explicitly require the
target_language
parameter for dubbing projects. This parameter has always been required - we’re just making it clearer in our docs. No code changes needed. -
Duration Validation: Added validation to ensure calculated duration makes sense, preventing zero-credit charges for invalid audio uploads.
Speech to Text
- Deterministic Sampling: Added
seed
parameter support for deterministic sampling, enabling reproducible speech-to-text results.
Forced Alignment
- Confidence Scoring: Added confidence scoring with
loss
field for words and overall transcript accuracy assessment using forced alignment.
Usage Analytics
- Workspace Breakdown: Added reporting workspace ID breakdown for character usage statistics, providing detailed usage insights across workspaces.
SDKs
- React Conversational AI SDK: Released v0.2.0 with support for Indian data residency and WebRTC mode for Conversational AI.
- Python SDK: Released v2.6.1 with enhanced Conversational AI capabilities and bug fixes.
- JavaScript SDK: Released v2.5.0 with improved Conversational AI SDK support and new features.
API
View API changes
Deprecations
POST /v1/convai/phone-numbers/create
has been deprecated in favor of POST /v1/convai/phone-numbers. Please note that migrating to the new endpoint requires a few adjustments:- Replace
provider_config
field withinbound_trunk
andoutbound_trunk
for SIP trunk configurations - Update response parsing to handle the new trunk configuration structure
- Replace
Schema Removals
- Removed
SIPTrunkConfigResponseModel
,SIPTrunkCredentials
,TransferToNumberToolConfig
- Removed
incomplete_expired
andcanceled
subscription statuses
New Features
Enhanced SIP Trunk Support
- SIP trunk configuration now uses separate inbound and outbound trunk configs instead of single configuration
- Deprecated
provider_config
field in SIP trunk response from the new endpoint (replaced withinbound_trunk
andoutbound_trunk
) - Inbound trunk access control with allowed addresses and phone numbers
- SIP URI transfer destinations alongside phone number transfers
- Transfer to number improvements (conference or SIP refer)
Agent Transfers
- Transfer delay configuration with
delay_ms
- Custom transfer messages
- Control over transferred agent first message behavior
Conversation Enhancements
- ElevenLabs Assistant integration tracking
- User ID tracking for conversation participants and initiators
- Audio data in post-call webhooks (configurable)
- MCP (Model Context Protocol) tool call details in conversation history
Widget Improvements
- Additional text customization options:
- Start chat button text
- Chatting status text
- Input placeholders for text-only and new conversations
API Improvements
Speech to Text
- Added deterministic sampling with
seed
parameter in Convert speech to text
Forced Alignment
- Added confidence scoring with
loss
field for words and overall transcript in Forced alignment
Usage Analytics
- Added reporting workspace ID breakdown for character stats in Get characters usage metrics
Tool Configuration
- Client tool response timeout increased from 30 to 120 seconds
Workspace Resources
- Added agent response tests resource type
Deprecations
- Phone number
provider_config
field (useinbound_trunk
/outbound_trunk
instead) phone_number
field in transfer configurations (usetransfer_destination
instead)
Text to Voice
- Voice Design: Launched new Text to Voice Design with Eleven v3 for creating custom voices from text descriptions.
Speech to Text
- Enhanced Diarization: Added
diarization_threshold
parameter to the Speech to Text endpoint. Fine-tune the balance between speaker accuracy and total speaker count by adjusting the threshold between 0.1 and 0.4.
Professional Voice Cloning
- Background Noise Removal: Added
remove_background_noise
to clean up voice samples using audio isolation models for better quality training data.
Studio
- Video Support Detection: Added
has_video
property to chapter responses to indicate whether chapters contain video content.
Workspaces
-
Service Account Groups: Service accounts can now be added to workspace groups for better permission management and access control.
-
Workspace Authentication: Added support for workspace authentication connections, enabling secure webhook tool integrations with external services.
SDKs
- Python SDK: Released v2.6.0 with latest API support and bug fixes.
- JavaScript SDK: Released v2.5.0 with latest API support and bug fixes.
- React Conversational AI SDK: Added WebRTC support in 0.2.0
API
View API changes
New Endpoints
- Added 2 new endpoints:
- Design a Voice - Create voice previews from text descriptions
- Create Voice From Preview - Convert voice previews to permanent voices
Updated Endpoints
Speech to Text
- Convert speech to text - Added
diarization_threshold
parameter for fine-tuning speaker separation
Voice Management
- Get voice sample audio - Added
remove_background_noise
query parameter and moved from request body to query parameters
Tools migration
- Conversational AI tools migration: The way tools in Conversational AI are handled is being migrated, please see the guide here to understand what’s changing and how to migrate
Text to Speech
- Audio tags automatic removal: Audio tags are now automatically removed when switching from V3 to V2 models, ensuring optimal compatibility and performance.
Conversational AI
- Tools management UI: Added a new comprehensive tools management interface for creating, configuring, and managing tools across all agents in your workspace.
- Streamlined agent creation: Introduced a new agent creation flow with improved user experience and better configuration options.
- Agent duplication: Added the ability to duplicate existing agents, allowing you to quickly create variations of successful agent configurations.
SIP Trunking
- Inbound media encryption: Added support for configurable inbound media encryption settings for SIP trunk phone numbers, enhancing security options.
Voices
- Famous voice category: Added a new “famous” voice category to the voice library, expanding the available voice options for users.
Dubbing
- CSV frame rate control: Added
csv_fps
parameter to control frame rate when parsing CSV files for dubbing projects, providing more precise timing control.
SDKs
- ElevenLabs JavaScript SDK v2.4.0: Released with new Conversational AI SDK support for Node.js. View release notes
- ElevenLabs Python SDK v2.5.0: Updated with enhanced Conversational AI capabilities. View release notes
API
View API changes
New Endpoints
Conversational AI
- Duplicate agent - Create a new agent by duplicating an existing one
- Create tool - Add a new tool to the available tools in the workspace
- List tools - Retrieve all tools available in the workspace
- Get tool - Retrieve a specific tool configuration
- Update tool - Update an existing tool configuration
- Delete tool - Remove a tool from the workspace
- Get tool dependent agents - List all agents that depend on a specific tool
Updated Endpoints
Conversational AI
-
Agent configuration:
- Added
built_in_tools
configuration for system tools management - Deprecated inline
tools
configuration in favor oftool_ids
for better tool management
- Added
-
Tool system:
- Refactored tool configuration structure to use centralized tool management
Dubbing
- CSV processing:
- Create dubbing project - Added
csv_fps
parameter for custom frame rate control
- Create dubbing project - Added
SIP Trunking
- Phone number creation:
- Create SIP trunk phone number - Added
inbound_media_encryption
parameter for security configuration
- Create SIP trunk phone number - Added
Voice Library
- Voice categories:
- Updated voice response models to include “famous” as a new voice category option
- Enhanced voice search and filtering capabilities
Conversational AI
- Dynamic variables in simulated conversations: Added support for dynamic variable population in simulated conversations, enabling more flexible and context-aware conversation testing scenarios.
- MCP server integration: Introduced comprehensive support for Model Context Protocol (MCP) servers, allowing agents to connect to external tools and services through standardized protocols with configurable approval policies.
- Burst pricing for extra concurrency: Added bursting capability for workspace call limits, automatically allowing up to 3x the configured concurrency limit during peak usage for overflow capacity.
Studio
- JSON content initialization: Added support for initializing Studio projects with structured JSON content through the
from_content_json
parameter, enabling programmatic project creation with predefined chapters, blocks, and voice configurations.
Workspaces
- Webhook management: Introduced workspace-level webhook management capabilities, allowing administrators to view, configure, and monitor webhook integrations across the entire workspace with detailed usage tracking and failure diagnostics.
API
View API changes
New Endpoints
Conversational AI - MCP Servers
- Create MCP server - Create a new MCP server configuration in the workspace
- List MCP servers - Retrieve all MCP server configurations available in the workspace
- Get MCP server - Retrieve a specific MCP server configuration from the workspace
- Update MCP server approval policy - Update the approval policy configuration for an MCP server
- Create MCP server tool approval - Add approval for a specific MCP tool when using per-tool approval mode
- Delete MCP server tool approval - Remove approval for a specific MCP tool when using per-tool approval mode
Workspace
- Get workspace webhooks - Retrieve all webhook configurations for the workspace with optional usage information
Updated Endpoints
Conversational AI
-
Agent simulation:
- Simulate conversation - Added
dynamic_variables
parameter for populating conversation context with runtime values - Simulate conversation stream - Added
dynamic_variables
parameter for streaming conversation simulations
- Simulate conversation - Added
-
Agent configuration:
- Agent platform settings - Added
bursting_enabled
parameter to control burst pricing for call limits
- Agent platform settings - Added
-
WebSocket events:
- Enhanced
ClientEvent
enum to includemcp_connection_status
for real-time MCP server monitoring
- Enhanced
-
Conversation charging:
- Added
is_burst
indicator to conversation metadata for tracking burst pricing usage
- Added
Studio
- Create Studio project - Added
from_content_json
parameter for JSON-based project setup
User Management
- User profile:
- Get user - Deprecated
can_use_delayed_payment_methods
field in user response model
- Get user - Deprecated
Subscription Management
- Subscription status:
- Removed
canceled
andunpaid
from available subscription status types, streamlining subscription state management
- Removed
Text to Speech
- Eleven v3 (alpha): Released Eleven v3 (alpha), our most expressive Text to Speech model, as a research preview.
Conversational AI
- Custom voice settings in multi-voice: Added support for configuring individual voice settings per supported voice in multi-voice agents, allowing fine-tuned control over stability, speed, similarity boost, and streaming latency for each voice.
- Silent transfer to human in Twilio: Added backend configuration support for silent (cold) transfer to human in the Twilio native integration, enabling seamless handoff without announcing the transfer to callers.
- Batch calling retry and cancel: Added support for retrying outbound calls to phone numbers that did not respond during a batch call, along with the ability to cancel ongoing batch operations for better campaign management.
- LLM pinning: Added support for versioned LLM models with explicit checkpoint identifiers
- Custom LLM headers: Added support for passing custom headers to custom LLMs
- Fixed issue in non-latin languages: Fixed an issue causing some conversations in non latin alphabet languages to fail.
SDKs
- Python SDK v2.3.0: Released Python SDK v2.3.0
- JavaScript SDK v2.2.0: Released JavaScript SDK v2.2.0
API
View API changes
New Endpoints
Conversational AI
-
Batch Calling:
- Cancel batch call - Cancel a running batch call and set all recipients to cancelled status
- Retry batch call - Retry a batch call by setting completed recipients back to pending status
-
Knowledge Base RAG:
- Get document RAG indexes - Get information about all RAG indexes of a knowledge base document
- Delete document RAG index - Delete a specific RAG index for a knowledge base document
- RAG index overview - Get total size and information of RAG indexes used by knowledge base documents
Updated Endpoints
Conversational AI
-
Supported Voices:
- Agent configuration - Added
optimize_streaming_latency
,stability
,speed
, andsimilarity_boost
parameters for per-voice TTS customization
- Agent configuration - Added
-
Transfer to Human:
- Agent configuration - Added
enable_client_message
parameter to control whether a message is played to the client during transfer
- Agent configuration - Added
-
Knowledge Base:
- Knowledge base documents now use
supported_usages
instead ofprompt_injectable
for better usage mode control - RAG index creation now returns enhanced response model with usage information
- Knowledge base documents now use
-
Custom LLM:
- Agent configuration - Added
request_headers
parameter for custom header configuration
- Agent configuration - Added
-
Widget Configuration:
- Agent platform settings - Added comprehensive
styles
configuration for widget appearance customization
- Agent platform settings - Added comprehensive
-
LLM:
- Added support for versioned LLM models with explicit version identifiers
Conversational AI
- Multi-voice support for agents: Enable conversational AI agents to dynamically switch between different voices during conversations for multi-character storytelling, language tutoring, and role-playing scenarios.
- Claude Sonnet 4 support: Added Claude Sonnet 4 as a new LLM option for conversational agents, providing enhanced reasoning capabilities and improved performance.
- Genesys Cloud integration: Introduced AudioHook Protocol integration for seamless connection with Genesys Cloud contact center platform.
- Force delete knowledge base documents: Added
force
parameter to knowledge base document deletion, allowing removal of documents even when used by agents. - Multimodal widget: Added text input and text-only mode defaults for better user experience with improved widget configuration.
API
View API changes
Updated Endpoints
Speech to Text
- Create transcript - Added
webhook
parameter for asynchronous processing with webhook delivery
Conversational AI
-
Knowledge Base:
- Delete knowledge base document - Added
force
query parameter to delete documents regardless of agent dependencies
- Delete knowledge base document - Added
-
Widget:
- Widget configuration - Added text input and text-only mode support for multi-modality
Forced Aligment
- Forced alignment improvements: Fixed a rare failure case in forced alignment processing to improve reliability.
Voices
- Live moderated voices filter: Added
include_live_moderated
query parameter to the shared voices endpoint, allowing you to include or exclude voices that are live moderated.
Conversational AI
- Secret dynamic variables: Added support for specifying dynamic variables as secrets with the
secret__
prefix. Secret dynamic variables can only be used in webhook tool headers and are never sent to an LLM, enhancing security for sensitive data. Learn more. - Skip turn system tool: Introduced a new system tool called skip_turn. When enabled, the agent will skip its turn if the user explicitly indicates they need a moment to think or perform an action (e.g., “just a sec”, “give me a minute”). This prevents turn timeout from being triggered during intentional user pauses. See the skip turn tool docs for more information.
- Text input support: Added text input support in websocket connections via “user_message” event with text field. Also added “user_activity” event support to indicate typing or other UI activity, improving agent turn-taking when there’s interleaved text and audio input.
- RAG chunk limit: Added ability to configure the maximum number of chunks collected during RAG retrieval, giving users more control over context window usage and costs.
- Enhanced widget configuration: Expanded widget customization options to include text input and text only mode.
- LLM usage calculator: Introduced tools to calculate expected LLM token usage and costs for agents, helping with cost estimation and planning.
Audio Native
- Accessibility improvements: Enhanced accessibility for the AudioNative player with multiple improvements:
- Added aria-labels for all buttons
- Enabled keyboard navigation for all interactive elements
- Made progress bar handle focusable and keyboard-accessible
- Improved focus indicator visibility for better screen reader compatibility
API
View API changes
New Endpoints
- Added 3 new endpoints:
- Get Agent Knowledge Base Size - Returns the number of pages in the agent’s knowledge base.
- Calculate Agent LLM Usage - Calculates expected number of LLM tokens needed for the specified agent.
- Calculate LLM Usage - Returns a list of LLM models and the expected cost for using them based on the provided values.
Updated Endpoints
Voices
- Get Shared Voices - Added
include_live_moderated
query parameter toGET /v1/shared-voices
to filter voices by live moderation status.
Conversational AI
-
Agent Configuration:
- Enhanced system tools with new
skip_turn
tool configuration - Improved RAG configuration with
max_retrieved_rag_chunks_count
parameter
- Enhanced system tools with new
-
Widget Configuration:
- Added support for text-only mode
-
Batch Calling:
- Batch call responses now include
phone_provider
field with default value “twilio”
- Batch call responses now include
Text to Speech
- Voice Settings:
- Added
quality
parameter to voice settings for controlling audio generation quality - Model response schema updated to include
can_use_quality
field
- Added