Branch merge previews; STT combined multichannel output

ElevenAgents

• Branch merge and rebase previews: Added Preview merged configuration (GET /v1/convai/agents/{agent_id}/branches/{source_branch_id}/merge-preview) and preview rebased configuration (GET /v1/convai/agents/{agent_id}/branches/{branch_id}/rebase-preview) to inspect merged or rebased agent configuration before committing. Both return MergePreviewResponseModel with the resulting config, overridden_fields, and source_identical_to_target.
• Branch usage metrics: List agent branches branch summary responses add optional calls_7d (integer) with seven-day call volume per branch.
• Auth connection status: Workspace auth connection response models replace OAuth-only OAuthConnectionStatus with shared AuthConnectionStatus (active, refresh_failed, revoked, credential_invalid). Bearer, Basic, mTLS, custom header, OAuth, OAuth2 JWT, Slack, URL secret and WhatsApp auth responses add optional status, status_detail and status_updated_at fields.
• Tool response filtering: HTTP and agent tool configuration schemas add optional response_filter to trim tool responses before they reach the LLM, with response_filter_mode and response_filters on related override models.
• Workflow phone transfers: Workflow phone-number transfer nodes add optional require_acceptance (boolean, default false) and optional uui (UUITransferConfig) for RFC 7433 hex User-to-User Information on SIP REFER transfers.
• Telephony agent assignment: Twilio, Exotel and SIP trunk phone-number import request schemas add optional agent_id (string) to assign an agent during number setup.
• Turn transcription on disabled interruptions: Turn configuration schemas add optional transcribe_on_disabled_interruptions (boolean, default false) to control whether user speech is transcribed when interruptions are disabled.
• Conversation sentiment: Conversation summary schemas add optional sentiment_analysis. Conversation user models add optional sentiment with frustrated-conversation references.

Speech to Text

• Combined multichannel output: Convert speech to text adds optional multichannel_output_style (separate default | combined) when use_multi_channel is enabled. Set combined to receive a single transcript with all channels merged and sorted by time instead of per-channel transcripts. Word-level responses include channel_index on each word when multichannel mode is active.

Text to Speech

• language_code behavior: TTS request schemas clarify that unsupported language_code values are ignored rather than rejected, and that language_code is not supported on multilingual_v2 models.

Workspaces

• Third-party API key disabling policy: Added Set workspace third-party disabling policy (POST /v1/workspaces/api-keys/third-party-disabling) for workspace-wide control over whether API key holders can self-disable keys via the third-party disable endpoint. Workspace API key create, patch and response models add optional third_party_disable_allowed (boolean).
• Bearer auth connection updates: Update workspace auth connection request union adds UpdateBearerAuthRequest for bearer token credential updates.
• Workspace permissions: Permission enums add conversation_privacy_manage and synthid_detector. Workspace group models add optional scim_group (string).

SDK Releases

JavaScript SDK

• v2.55.0 - Regenerated from the latest OpenAPI schema with branch merge and rebase preview clients, branch call-volume metrics, auth connection status fields, tool response filtering types, speech-to-text combined multichannel output, and workspace third-party API key disabling policy.

Python SDK

• v2.55.0 - Regenerated from the latest OpenAPI schema with branch merge and rebase preview clients, branch call-volume metrics, auth connection status fields, tool response filtering models, speech-to-text combined multichannel output, and workspace third-party API key disabling policy.

Packages

• @elevenlabs/client@1.13.0 - sendFeedback(like, eventId?) accepts an optional event_id to rate a specific past message. canSendFeedback now reflects connection state so feedback can be sent for any message while the session is live.
• @elevenlabs/client@1.14.0 - sendFeedback accepts null as the first argument to clear feedback on an event (score: null).
• @elevenlabs/react@1.8.0 and @elevenlabs/react@1.9.0 - Exposed the per-message and clear-feedback sendFeedback changes from @elevenlabs/client@1.13.0 and @elevenlabs/client@1.14.0 in React hooks.
• @elevenlabs/react-native@1.2.11 and @elevenlabs/react-native@1.2.12 - Dependency alignment to @elevenlabs/client@1.13.0–1.14.0 and @elevenlabs/react@1.8.0–1.9.0.
• @elevenlabs/types@0.16.0, @elevenlabs/convai-widget-core@0.14.6–0.14.8 and @elevenlabs/convai-widget-embed@0.14.6–0.14.8 - Dependency alignment to @elevenlabs/client@1.13.0–1.14.0.

Android SDK

• v0.10.0 - Exposed reconciled message transcript as StateFlow. Deprecated text and agent callbacks in favor of event-id variants.
• v0.11.0 - Added audio frame callback for per-frame audio inspection during conversations.

iOS SDK

• v3.2.2 - Fixed LiveKit room delegate method implementation for correct room event handling.

API