Changelog

December 8, 2025

Agents Platform

Music Generation

  • Word timestamps: Added word-level timestamps to music generation with detailed responses. Enable with the with_timestamps parameter.
  • Fine-tuning support: Added finetune_id parameter to music generation endpoints for using custom music fine-tunes.
  • C2PA content signing: Added sign_with_c2pa option to music generation requests for content authenticity and provenance.

Voices

  • Voice settings expansion: Added voice_stability, voice_similarity, and voice_style parameters to voice endpoints for more granular control.
  • Pagination improvements: Clarified pagination behavior for Get all voices v2 endpoint with better documentation of next_page_token, has_more, and total_count fields.

ElevenCreative Studio

  • Voice settings override: Added voice_settings parameter to project creation for per-project voice configuration.

Webhook Tools

  • Custom request headers: Added request_headers support to Webhook tool configuration for custom authentication and metadata.

Billing

  • Schema improvements: Introduced BillingPeriod and CharacterRefreshPeriod enums for better type safety in subscription models.

Knowledge Base

  • RAG query rewriting: Added query_rewrite_prompt_override to RAG configuration for customizing query rewriting behavior.

SDK Releases

JavaScript SDK

  • v2.27.0 - Updated API schema with latest changes including Twilio registration endpoint and music word timestamps
  • v2.26.0 - Added previous_text event support to Scribe and updated event types

Python SDK

  • v2.26.0 - Fixed websocket disconnection code for user-triggered closures and updated API schema
  • v2.25.0 - Added on-premises agent configuration support, previous_text event support to Scribe, and improved CI reliability

Packages

Android SDK

  • v0.7.0 - Added sendToolResult function for client tool support

iOS SDK

  • v3.0.0 - Major release with breaking changes including onDisconnect now receives disconnect reason, added .thinking agent state, updated LiveKit to 2.10.0+, removed AsyncAlgorithms dependency, and added Swift 5.9+ support (previously required Swift 6.0). Includes SDK hardening, improved error handling, alignment data fixes, and agent response metadata support

ElevenLabs CLI

API

New Endpoints

Updated Endpoints

Agents Platform

  • Create agent
    • Added template to AgentDefinitionSource enum
  • Get conversation
    • Added direction field to WhatsAppConversationInfo
    • Added support for API Integration Webhook tool calls and results in conversation transcripts

Music Generation

  • Compose music with detailed response
    • Added optional with_timestamps parameter (boolean) to enable word-level timestamps
    • Added words_timestamps field to response containing array of WordTimestamp objects
    • Added optional finetune_id parameter (string) for custom music fine-tuning
    • Added optional sign_with_c2pa parameter (boolean) for content authenticity signing
  • Compose music
    • Added optional finetune_id parameter (string) for custom music fine-tuning
    • Added optional sign_with_c2pa parameter (boolean) for content authenticity signing
  • Stream music
    • Added optional finetune_id parameter (string) for custom music fine-tuning
  • Stem separation
    • Added optional sign_with_c2pa parameter (boolean) for content authenticity signing

ElevenCreative Studio

  • Add project
    • Added optional voice_settings parameter (array) for per-project voice configuration JSON

Knowledge Base

Webhook Tools

  • Webhook tool configuration endpoints
    • Added request_headers field (object) to webhook tool API schema configuration for custom HTTP headers

Voices

  • Get voice
    • Added optional voice_stability parameter
    • Added optional voice_similarity parameter
    • Added optional voice_style parameter
  • Get all voices v2
    • Updated next_page_token query parameter description to clarify pagination with has_more field
    • Updated include_total_count query parameter description to note snapshot nature and performance implications
    • Added descriptions for response fields: voices, has_more, total_count, next_page_token
    • Changed next_page_token parameter to allow null values
    • Changed include_total_count parameter to allow null values

Dubbing

  • Dub a video or audio file
    • Made background field nullable in dubbing mix input
    • Made foreground field nullable in dubbing mix input
  • Get dubbing project metadata
    • Made background and foreground fields nullable in response (breaking change - removed nested properties src, content_type, bucket_name, random_path_slug, duration_secs, is_audio, url)

Text to Speech

  • All TTS endpoints
    • Added optional voice_stability parameter where voice settings are supported
    • Added optional voice_similarity parameter where voice settings are supported
    • Added optional voice_style parameter where voice settings are supported
    • Simplified apply_text_normalization description (removed plan-specific note)

Lists and Sorting

  • Get agents
    • Changed sort_by query parameter to allow null values and removed default value
  • Get knowledge base
    • Changed sort_by query parameter to allow null values and removed default value

Billing

  • Subscription endpoints
    • Introduced BillingPeriod enum (replaced inline enum values)
    • Introduced CharacterRefreshPeriod enum (replaced inline enum values)
    • Updated subscription and tier change models to use enum references