Conversational AI
- Default LLM update: Changed the default agent LLM from Gemini 1.5 Flash to Gemini 2.0 Flash for improved performance.
- Fixed incorrect conversation abandons: Improved detection of conversation continuations, preventing premature abandons when users repeat themselves.
- Twilio information in history: Added Twilio call details to conversation history for better tracking.
- Knowledge base redesign: Redesigned the knowledge base interface.
- System dynamic variables: Added system dynamic variables to use time, conversation id, caller id and other system values as dynamic variables in prompts and tools.
- Twilio client initialisation: Adds an agent level override for conversation initiation client data twilio webhook.
- RAG chunks in history: Added retrieved chunks by RAG to the call transcripts in the history view.
Speech to Text
- Reduced pricing: Reduced the pricing of our Scribe model, see more here.
- Improved VAD detection: Enhanced Voice Activity Detection with better pause detection at segment boundaries and improved handling of silent segments.
- Enhanced diarization: Improved speaker clustering with a better ECAPA model, symmetric connectivity matrix, and more selective speaker embedding generation.
- Fixed ASR bugs: Resolved issues with VAD rounding, silence and clustering that affected transcription accuracy.
Studio
- Disable publishing UI: Added ability to disable the publishing interface for specific workspace members to support enterprise workflows.
- Snapshot API improvement: Modified endpoints for project and chapter snapshots to return an empty list instead of throwing errors when snapshots can’t be downloaded.
- Disabled auto-moderation: Turned off automatic moderation based on Text to Speech generations in Studio.
Workspaces
- Fixed API key editing: Resolved an issue where editing workspace API keys would reset character limits to zero, causing the keys to stop working.
- Optimized free subscriptions: Fixed an issue with refreshing free subscription character limits,
API
View API changes
New Endpoints
- Added 3 new endpoints:
Updated Endpoints
Dubbing
- Updated Dubbing endpoints:
- Dub a video or audio file - Added
use_replacement_voices_from_library
property and madesource_path
,target_language
,source_language
nullable - Resource dubbing - Made
language_codes
array nullable - Add language to dubbing resource - Made
language_code
nullable - Add speaker segment - Made
text
nullable - Translate dubbing resource - Made
target_languages
array nullable - Update dubbing segment - Made
start_time
andend_time
nullable
- Dub a video or audio file - Added
Project Management
- Updated Project endpoints:
- Add project - Made
metadata
,project_name
,description
nullable - Create podcast - Made
title
,description
,author
nullable - Get project - Made
last_modified_at
,created_at
,project_name
nullable - Add chapter - Made
chapter_id
,word_count
,statistics
nullable - Update chapter - Made
content
andblocks
properties nullable
- Add project - Made
Conversational AI
- Updated Conversational AI endpoints:
- Update agent - Made
conversation_config
,platform_settings
nullable and addedworkspace_overrides
property - Create agent - Made
agent_name
,prompt
,widget_config
nullable and addedworkspace_overrides
property - Add to knowledge base - Made
document_name
nullable - Get conversation - Added
twilio_call_data
model and madetranscript
,metadata
nullable
- Update agent - Made
Text to Speech
- Updated Text to Speech endpoints:
- Convert text to speech - Made
voice_settings
,text_input
nullable and deprecateduse_pvc_as_ivc
property - Stream text to speech - Made
voice_settings
,text_input
nullable and deprecateduse_pvc_as_ivc
property - Convert with timestamps - Made
character_alignment
andword_alignment
nullable
- Convert text to speech - Made
Voice Management
- Updated Voice endpoints:
- Create voice previews - Added
loudness
,quality
,guidance_scale
properties - Create voice from preview - Added
speaker_separation
properties and madevoice_id
,name
,labels
nullable - Get voice - Added
speaker_boost
,speaker_clarity
,speaker_isolation
properties
- Create voice previews - Added
Speech to Text
- Updated Speech to Text endpoint:
- Convert speech to text - Added
biased_keywords
property
- Convert speech to text - Added
Other Updates
- Download history - Added application/zip content type and 400 response
- Add pronunciation dictionary from file - Made
dictionary_name
anddescription
nullable
Conversational AI
- HIPAA compliance: Conversational AI is now HIPAA compliant on appropriate plans, when a BAA is signed, zero-retention mode is enabled and appropriate LLMs are used. For access please contact sales
- Cascade LLM: Added dynamic dispatch during the LLM step to other LLMs if your default LLM fails. This results in higher latency but prevents the turn failing.
- Better error messages: Added better error messages for websocket failures.
- Audio toggling: Added ability to select only user or agent audio in the conversation playback.
Scribe
- HIPAA compliance: Added a zero retention mode to Scribe to be HIPAA compliant.
- Diarization: Increased time length of audio files that can be transcribed with diarization from 8 minutes to 2 hours.
- Cheaper pricing: Updated Scribe’s pricing to be cheaper, as low as $0.22 per hour for the Business tier.
- Memory usage: Shipped improvements to Scribe’s memory usage.
- Fixed timestamps: Fixed an issue that was causing incorrect timestamps to be returned.
- Biased keywords: Added biased keywords to improve Scribe’s performance.
Text to Speech
- Pronunciation dictionaries: Fixed pronunciation dictionary rule application for replacements that contain symbols.
Dubbing
- Studio support: Added support for creating dubs with
dubbing_studio
enabled, allowing for more advanced dubbing workflows beyond one-off dubs.
Voices
- Verification: Fixed an issue where users on probation could not verify their voice clone.
API
View API changes
New Endpoints
- Added 7 new endpoints:
Updated Endpoints
Studio Projects
- Updated Studio project endpoints to add
source_type
property and deprecatequality_check_on
andquality_check_on_when_bulk_convert
properties:
Voice Management
- Updated Voice endpoints with several property changes:
- Get voice - Made several properties optional and added
preview_url
- Create voice - Made several properties optional and added
preview_url
- Create voice from preview - Made several properties optional and added
preview_url
- Get similar voices - Made
language
,description
,preview_url
, andrate
properties optional
- Get voice - Made several properties optional and added
Conversational AI
- Updated Conversational AI agent endpoints:
- Update agent - Modified
conversation_config
,agent
,platform_settings
, andwidget
properties - Create agent - Modified
conversation_config
,agent
,prompt
, platform_settings, widget properties and addedshareable_page_show_terms
- Get agent - Modified
conversation_config
,agent
,platform_settings
, andwidget
properties - Get widget - Modified
widget_config
property and addedshareable_page_show_terms
- Update agent - Modified
Knowledge Base
- Updated Knowledge Base endpoints to add metadata property:
Other Updates
- Dub a video or audio file - Added
dubbing_studio
property - Convert text to sound effects - Added
output_format
query parameter - Convert speech to text - Added
enable_logging
query parameter - Get secrets - Modified
secrets
andused_by
properties - Get all pronunciation dictionaries - Made
next_cursor
property optional
Removed Endpoints
-
Temporarily removed Conversational AI tools endpoints:
- Get tool
- List tools
- Update tool
- Create tool
- Delete tool
Dubbing
- Scribe for speech recognition: Dubbing Studio now uses Scribe by default for speech recognition to improve accuracy.
Speech to Text
- Fixes: Shipped several fixes improving the stability of Speech to Text.
Conversational AI
- Speed control: Added speed control to an agent’s settings in Conversational AI.
- Post call webhook: Added the option of sending post-call webhooks after conversations are completed.
- Improved error messages: Added better error messages to the Conversational AI websocket.
- Claude 3.7 Sonnet: Added Claude 3.7 Sonnet as a new LLM option in Conversational AI.
API
View API changes
New Endpoints
- Added new Dubbing resource management endpoints:
- for adding languages to dubs
- for retrieving dubbing resources
- for creating segments
- for modifying segments
- for removing segments
- for dubbing segments
- for transcribing segments
- for translating segments
- Added Knowledge Base RAG indexing endpoint
- Added Studio snapshot retrieval endpoints for projects and chapters
Updated Endpoints
- Added
prompt_injectable
property to knowledge base endpoints - Added
name
property to Knowledge Base document creation and retrieval endpoints: - Added
speed
property to agent creation - Removed
secrets
property from agent endpoints (now handled by dedicated secrets endpoints) - Added secret deletion endpoint for removing secrets
- Removed
secrets
property from settings endpoints
Speech to Text
- ElevenLabs launched a new state of the art Speech to Text API available in 99 languages.
Text to Speech
- Speed control: Added speed control to the Text to Speech API.
Studio
- Auto-assigned projects: Increased token limits for auto-assigned projects from 1 month to 3 months worth of tokens, addressing user feedback about working on longer projects.
- Language detection: Added automatic language detection when generating audio for the first time, with suggestions to switch to Eleven Turbo v2.5 for languages not supported by Multilingual v2 (Hungarian, Norwegian, Vietnamese).
- Project export: Enhanced project exporting in ElevenReader with better metadata tracking.
Dubbing
- Clip overlap prevention: Added automatic trimming of overlapping clips in dubbing jobs to ensure clean audio tracks for each speaker and language.
Voice Management
- Instant Voice Cloning: Improved preview generation for Instant Voice Cloning v2, making previews available immediately.
Conversational AI
- Agent ownership: Added display of agent creators in the agent list, improving visibility and management of shared agents.
Web app
- Dark mode: Added dark mode to the web app.
API
View API changes
- Launched /v1/speech-to-text endpoint
- Added
agents.level
property to Conversational AI agents endpoint - Added
platform_settings
to Conversational AI agent endpoint - Added
expandable
variant towidget_config
, with configuration optionsshow_avatar_when_collapsed
anddisable_banner
to Conversational AI agent widget endpoint - Added
webhooks
property andused_by
tosecrets
to secrets endpoint - Added
verified_languages
to voices endpoint - Added
speed
property to voice settings endpoints - Added
verified_languages
,is_added_by_user
tovoices
andmin_notice_period_days
query parameter to shared voices endpoint - Added
verified_languages
,is_added_by_user
tovoices
in similar voices endpoint - Added
search
,show_only_owned_documents
,use_typesense
query parameters to knowledge base endpoint - Added
used_by
to Conversation AI secrets endpoint - Added
invalidate_affected_text
property to Studio pronunciation dictionaries endpoint
Conversational AI
- Tool calling fix: Fixed an issue where tool calling was not working with agents using gpt-4o mini. This was due to a breaking change in the OpenAI API.
- Tool calling improvements: Added support for tool calling with dynamic variables inside objects and arrays.
- Dynamic variables: Fixed an issue where dynamic variables of a conversation were not being displayed correctly.
Voice Isolator
- Fixed: Fixed an issue that caused the voice isolator to not work correctly temporarily.
Workspace
- Billing: Improved billing visibility by differentiating rollover, cycle, gifted, and usage-based credits.
- Usage Analytics: Improved usage analytics load times and readability.
- Fine grained fiat billing: Added support for customizable pricing based on several factors.
API
View API changes
- Added
phone_numbers
property to Agent responses - Added usage metrics to subscription_extras in User endpoint:
unused_characters_rolled_over_from_previous_period
overused_characters_rolled_over_from_previous_period
usage
statistics
- Added
enable_conversation_initiation_client_data_from_webhook
to Agent creation - Updated Agent endpoints with consolidated settings for:
platform_settings
overrides
safety
- Deprecated
with_settings
parameter in Voice retrieval endpoint
Conversational AI
- Updated Pricing: Updated self-serve pricing for Conversational AI with reduced cost and a more generous free tier.
- Knowledge Base UI: Created a new page to easily manage your knowledge base.
- Live calls: Added number of live calls in progress in the user dashboard and as a new endpoint.
- Retention: Added ability to customize transcripts and audio recordings retention settings.
- Audio recording: Added a new option to disable audio recordings.
- 8k PCM support: Added support for 8k PCM audio for both input and output.
Studio
- GenFM: Updated the create podcast endpoint to accept multiple input sources.
- GenFM: Fixed an issue where GenFM was creating empty podcasts.
Enterprise
- New workspace group endpoints: Added new endpoints to manage workspace groups.
API
Deprecated Endpoints
Studio (formerly Projects)
All /v1/projects/*
endpoints have been deprecated in favor of the new /v1/studio/projects/*
endpoints. The following endpoints are now deprecated:
- All operations on
/v1/projects/
- All operations related to chapters, snapshots, and content under
/v1/projects/*
Conversational AI
POST /v1/convai/add-tool
- UsePOST /v1/convai/tools
instead
Breaking Changes
DELETE /v1/convai/agents/{agent_id}
- Response type is no longer an objectGET /v1/convai/tools
- Response type changed from array to object with atools
property
Modified Endpoints
Conversational AI Updates
GET /v1/convai/agents/{agent_id}
- Updated conversation configuration and agent propertiesPATCH /v1/convai/agents/{agent_id}
- Addeduse_tool_ids
parameter for tool managementPOST /v1/convai/agents/create
- Added tool integration viause_tool_ids
Knowledge Base & Tools
GET /v1/convai/agents/{agent_id}/knowledge-base/{documentation_id}
- Addedname
andaccess_level
propertiesGET /v1/convai/knowledge-base/{documentation_id}
- Addedname
andaccess_level
propertiesGET /v1/convai/tools/{tool_id}
- Addeddependent_agents
propertyPATCH /v1/convai/tools/{tool_id}
- Addeddependent_agents
property
GenFM
POST /v1/projects/podcast/create
- Added support for multiple input sources
New Endpoints
Studio (formerly Projects)
New endpoints replacing the deprecated /v1/projects/*
endpoints
GET /v1/studio/projects
: List all projectsPOST /v1/studio/projects
: Create a projectGET /v1/studio/projects/{project_id}
: Get project detailsDELETE /v1/studio/projects/{project_id}
: Delete a project
Knowledge Base Management
GET /v1/convai/knowledge-base
: List all knowledge base documentsDELETE /v1/convai/knowledge-base/{documentation_id}
: Delete a knowledge baseGET /v1/convai/knowledge-base/{documentation_id}/dependent-agents
: List agents using this knowledge base
Workspace Groups - New enterprise features for team management
GET /v1/workspace/groups/search
: Search workspace groupsPOST /v1/workspace/groups/{group_id}/members
: Add members to a groupPOST /v1/workspace/groups/{group_id}/members/remove
: Remove members from a group
Tools
POST /v1/convai/tools
: Create new tools for agents
Socials
- ElevenLabs Developers: Follow our new developers account on X @ElevenLabsDevs
Conversational AI
- Agent monitoring: Added a new dashboard for monitoring conversational AI agents’ activity. Check out your’s here.
- Proactive conversations: Enhanced capabilities with improved timeout retry logic. Learn more
- Tool calls: Fixed timeout issues occurring during tool calls
- Allowlist: Fixed implementation of allowlist functionality.
- Content summarization: Added Gemini as a fallback model to ensure service reliability
- Widget stability: Fixed issue with dynamic variables causing the Conversational AI widget to fail
Reader
- Trending content: Added carousel showcasing popular articles and trending content
- New publications: Introduced dedicated section for recent ElevenReader Publishing releases
Studio (formerly Projects)
- Projects is now Studio and is now generally available to everyone
- Chapter content editing: Added support for editing chapter content through the public API, enabling programmatic updates to chapter text and metadata
- GenFM public API: Added public API support for podcast creation through GenFM. Key features include:
- Conversation mode with configurable host and guest voices
- URL-based content sourcing
- Customizable duration and highlights
- Webhook callbacks for status updates
- Project snapshot IDs for audio downloads
SDKs
- Swift: fixed an issue where resources were not being released after the end of a session
- Python: added uv support
- Python: fixed an issue where calls were not ending correctly
API
View API changes
- Added POST
v1/workspace/invites/add-bulk
endpoint to enable inviting multiple users simultaneously - Added POST
v1/projects/podcast/create
endpoint for programmatic podcast generation through GenFM - Added ‘v1/convai/knowledge-base/:documentation_id’ endpoints with CRUD operations for Conversational AI
- Added PATCH
v1/projects/:project_id/chapters/:chapter_id
endpoint for updating project chapter content and metadata - Added
group_ids
parameter to Workspace Invite endpoint for group-based access control - Added structured
content
property to Chapter response objects - Added
retention_days
anddelete_transcript_and_pii
data retention parameters to Agent creation - Added structured response to AudioNative content
- Added
convai_chars_per_minute
usage metric to User endpoint - Added
media_metadata
field to Dubbing response objects - Added GDPR-compliant
deletion_settings
to Conversation responses - Deprecated Knowledge Base legacy endpoints:
- POST
/v1/convai/agents/{agent_id}/add-to-knowledge-base
- GET
/v1/convai/agents/{agent_id}/knowledge-base/{documentation_id}
- POST
- Updated Agent endpoints with consolidated privacy control parameters
Docs
- Shipped our new docs: we’re keen to hear your thoughts, you can reach out by opening an issue on GitHub or chatting with us on Discord
Conversational AI
- Dynamic variables: Available in the dashboard and SDKs. Learn more
- Interruption handling: Now possible to ignore user interruptions in Conversational AI. Learn more
- Twilio integration: Shipped changes to increase audio quality when integrating with Twilio
- Latency optimization: Published detailed blog post on latency optimizations. Read more
- PCM 8000: Added support for PCM 8000 to Conversational AI agents
- Websocket improvements: Fixed unexpected websocket closures
Projects
- Auto-regenerate: Auto-regeneration now available by default at no extra cost
- Content management: Added
updateContent
method for dynamic content updates - Audio conversion: New auto-convert and auto-publish flags for seamless workflows
API
View API changes
- Added
Update Project
endpoint for project editing - Added
Update Content
endpoint for AudioNative content management - Deprecated
quality_check_on
parameter in project operations. It is now enabled for all users at no extra cost - Added
apply_text_normalization
parameter to project creation with modes ‘auto’, ‘on’, ‘apply_english’ and ‘off’ for controlling text normalization during project creation - Added alpha feature
auto_assign_voices
in project creation to automatically assign voices to phrases - Added
auto_convert
flag to project creation to automatically convert projects to audio - Added support for creating Conversational AI agents with dynamic variables
- Added
voice_slots_used
toSubscription
model to track number of custom voices used in a workspace to theUser
endpoint - Added
user_id
field toUser
endpoint - Marked legacy AudioNative creation parameters (
image
,small
,sessionization
) as deprecated parameters - Agents platform now supports
call_limits
containing eitheragent_concurrency_limit
ordaily_limit
or both parameters to control simultaneous and daily conversation limits for agents - Added support for
language_presets
inconversation_config
to customize language-specific settings
SDKs
- Cross-Runtime Support: Now compatible with Bun 1.1.45+ and Deno 2.1.7+
- Regenerated SDKs: We regenerated our SDKs to be up to date with the latest API spec. Check out the latest Python SDK release and JS SDK release
- Dynamic Variables: Fixed an issue where dynamic variables were not being handled correctly, they are now correctly handled in all SDKs
Product
Conversational AI
- Additional languages: Add a language dropdown to your widget so customers can launch conversations in their preferred language. Learn more here.
- End call tool: Let the agent automatically end the call with our new “End Call” tool. Learn more here
- Flash default: Flash, our lowest latency model, is now the default for new agents. In your agent dashboard under “voice”, you can toggle between Turbo and Flash. Learn more about Flash here.
- Privacy: Set concurrent call and daily call limits, turn off audio recordings, add feedback collection, and define customer terms & conditions.
- Increased tool limits: Increase the number of tools available to your agent from 5 to 15. Learn more here.
Product
- Workspace Groups and Permissions: Introduced new workspace group management features to enhance access control within organizations. Learn more.