Registro delle modifiche

• Fast LLM service tier: Agents and workflow overrides accept service_tier (standard or fast) on supported models. List LLMs returns available_service_tiers for each model, and the LLM usage calculator accepts service_tier.
• Knowledge base crawl exclusions: Create crawl job accepts exclude_patterns, and the whole-website crawl dialog adds an Exclude patterns field. Matching URLs are skipped.
• Procedures analytics: The Procedures tab on the agent analytics dashboard is available to every workspace. Its Procedure invocations chart shows how often each procedure runs over time, grouped by procedure or by agent, and its tooltip shows whether a procedure is structured or free-form.
• Start procedures at conversation start: Conversation initiation client data accepts start_procedure_ids, up to five free-form procedures that start when the conversation starts. The agent must have enable_procedure_ids_from_client enabled; structured procedures and unknown IDs fail the conversation start.
• Structured procedure steps: Structured procedures can use the end_procedure system tool as a step, and the End step is relabeled End conversation. Sub-procedure and end steps now compile to system tool nodes, so agents start and end the intended procedure more reliably.
• Channel integrations out of alpha: The Slack, Telegram, Custom Channel and Intercom integrations are no longer in alpha. Freshdesk remains in alpha.
• Slack thread replies: The Slack Channel Message trigger adds a Respond to setting (response_mode), so an agent can keep replying in a thread after a single mention. Mentioning the agent with only stop, mute or quiet silences it in that thread until it is mentioned again, and events that Slack delivers twice get one reply.
• Test run names: Run tests accepts an optional name, which test invocations and their summaries return. PATCH /v1/convai/test-invocations/{test_invocation_id} renames a run, and setting name to null restores the generated title.
• Branch descriptions: Branch descriptions can be edited from the branches table with Update branch (description, up to 4,096 characters) and appear in the version tooltip and version graph.
• Agent duplication keeps traffic splits: Duplicating an agent copies its live traffic split across the copied branches. The resulting deployment records duplicate as its deployment source.
• Delete environment variables: DELETE /v1/convai/environment-variables/{env_var_id} deletes an environment variable.
• Widget fullscreen on mobile: Widget configuration adds mobile_fullscreen (default true), with a Fullscreen on mobile switch in the dashboard. Set it to false to keep the compact layout on phones. See Widget.
• Issues: Triage is renamed Issues in the agents dashboard, and triage tickets are now called issues. Every QA comment and flag_issue_for_review call opens its own issue, and an issue can be reopened while the conversation has another open issue. The API endpoints keep their triage-tickets paths. See Triage.
• Prompt caching guidance: The system prompt editor flags system variables that change on every turn and prevent prompt caching, and Spotlight adds an Improve prompt caching recommendation for affected agents.
• Realtime voice mode: Switching an agent to Realtime voice mode in the dashboard now selects Eleven Realtime v1 Max. Realtime agents always run tool calls in parallel, so the Parallel tool calling toggle is removed from Realtime model settings. See Realtime models.
• Analytics: Workflow analytics can be filtered by channel, and the Guardrails tab is shown to all users.
• Analysis LLMs: claude-sonnet-5-5 can be selected as the analysis LLM for evaluation criteria and data collection, both for the agent and per item. Agents on Claude Sonnet 5.5 can also set reasoning effort to none.
• Conversation cost: Conversation charging adds voice_surcharge_charge, the credits charged as the voice actor reward for the Voice Library voices a conversation used. It is not included in cost.
• Call duration and billing: Call charges and stored call duration stop when the call ends, so teardown time after the call is no longer billed or counted. Calls no longer continue for up to 50 seconds after ending when a knowledge base lookup is in progress.
• Telephony: SIP trunk calls forward the User-To-User (UUI) header to the conversation initiation webhook. API keys with an IP allowlist now authenticate on the Genesys, Avaya, AudioCodes and Amazon Connect connector WebSockets. Batch call recipients whose call cannot be placed are marked failed instead of staying dispatched.
• Observability: OpenTelemetry post-call webhook agent turn spans add elevenlabs.rag.chunks and elevenlabs.rag.used_chunk_ids, matching the JSON post-call webhook. See OpenTelemetry traces.
• Guardrails: In voice conversations, the prompt injection guardrail now evaluates the user turn being answered instead of the agent’s previous message. Conversations on asynchronous channels such as Zendesk, Intercom and Custom Channel that a guardrail blocks now report the guardrail as the termination reason.
• Zero Retention Mode: Synthetic voice detection is skipped for conversations in Zero Retention Mode.
• WhatsApp: WhatsApp conversations resumed by a reply to a batch call template keep their batch_call metadata and batch ID.
• Phone number secrets: Workspace secrets used as a Twilio auth token or an Exotel API token on a phone number show as in use and cannot be deleted while the number depends on them.
• Fixes: Text conversations end as soon as the end_call tool runs instead of waiting for the next user message. Voice agents no longer go silent when a turn is cancelled before any audio is sent. The soft timeout no longer fires right after the first message or after tool calls on Eleven v4 voices. Realtime agents with sub-agent, agent tool or prompt say nodes that inherit the LLM can be saved and published. Agent tools that use OAuth2 connections no longer fail with expired tokens when the provider rotates refresh tokens. The nemotron-35-super-vl-nvfp4 context limit is raised from 64,000 to 131,072 tokens.

• Clone strength: clone_strength (0 to 1) in Text to Speech voice_settings and Text to Dialogue settings controls how closely a Professional Voice Clone fine-tuned for a v4 model follows its samples. The recommended value for most use cases is 0. Edit voice settings stores clone_strength and Get voice settings returns it.
• PVC and IVC on v4 dialogue: On the Text to Dialogue endpoints, clone_strength now decides whether a v4 PVC runs as a PVC or an IVC, and use_pvc_as_ivc is deprecated.

• New endpoint paths: Voice Changer is documented at POST /v1/voice-changer/{voice_id} and POST /v1/voice-changer/{voice_id}/stream. The /v1/speech-to-speech/{voice_id} paths keep working but are deprecated and removed from the API reference. The Python and JavaScript SDKs call the new paths from v2.75.0, and the SDK method names are unchanged for now. In the next major SDK version, client.speechToSpeech will be deprecated in favor of client.voiceChanger to match the endpoint. See Voice changer.

• Expiring service account API keys: Service account API keys accept expires_at_unix on create and update, between 15 minutes and 90 days in the future. Later expiries are rejected with 400 invalid_api_key_expiry. On update, pass "clear" to remove an expiry.
• Group concurrency limits enforced: The workspace group concurrency limits (group_concurrency_limit, group_dubbing_concurrency_limit and group_music_concurrency_limit) are enforced for Text to Speech, Voice Changer, Music and Dubbing requests.
• Voice cloning permissions: Members without the Create instant voice clone or Create professional voice clone permission can no longer create clones, even with general voice access.
• SCIM group seat types: Workspaces that use SCIM without SCIM routing can assign a seat type to SCIM-synced groups from the Groups page.
• Fixes: Delete invite returns 404 invite_not_found for an invite that does not exist, instead of a 500 error.

• Shorter realtime silence thresholds: Realtime Speech to Text honors vad_silence_threshold_secs values below 0.5 seconds, which were previously treated as 0.5. The minimum accepted value is lowered from 0.3 to about 0.19 seconds.
• Webhook retries: Transcription and error webhooks are retried on failure when the webhook’s retry setting is on. See Speech to Text webhooks.

• Legacy endpoints deprecated: The /v1/dubbing endpoints outside /v1/dubbing/project, including Dub a video or an audio file and List dubs, are marked deprecated in the API reference.
• Transcript downloads: The dubbing project menu can download target language transcripts as JSON, and as WebVTT subtitles for recent dubs.

• Media folders: Workspace library files can be organized into folders in the Studio media browser.
• Video clip actions: Video clips offer voice changer and voice isolator actions.
• Video to music: Studio’s video to music workflow uses Music v2.5 by default.

• Retired models: Image & Video and Flows requests for a retired model fail before generation with a 410 model_retired error that names the replacement model. Flows preflight reports the error on the affected node.
• Fixes: Generations wait for a just-uploaded reference asset to finish processing instead of failing.

• Fixes: Cantonese Professional Voice Clone samples are no longer rejected when language detection reports Chinese, and adding PVC samples no longer fails with a 500 error when language detection is unavailable.

• Minimum charge: Text to Speech and Speech to Text requests priced below one credit are charged one credit, and refunds return exactly the credits that were charged.
• Business plan image and video pricing: Business plans on the current pricing pay the same image and video credit rate as other self-serve plans, about 17% fewer credits per image and per video second than before.

• OAuth scope: OAuth clients can request the realtime_translation scope.

JavaScript SDK

• v2.75.0 - client.speechToSpeech.convert and client.speechToSpeech.stream now call POST /v1/voice-changer/{voice_id} and its /stream path. Added client.environmentVariables.delete, client.conversationalAi.tests.invocations.update for renaming a test invocation, and an optional name on client.conversationalAi.agents.runTests. Also adds serviceTier on the LLM usage calculators, excludePatterns on knowledge base crawl jobs, expiresAtUnix on service account API keys, cloneStrength in voice settings, startProcedureIds in conversation initiation client data and the widget mobileFullscreen setting. The legacy dubbing list, create, get and delete methods are marked deprecated, and the branch rebase request type BranchesRebaseRequest is renamed to BodyRebaseABranchOntoMainV1ConvaiAgentsAgentIdBranchesBranchIdRebasePost.

Python SDK

• v2.75.0 - Added the callback_disconnect option to Conversation and AsyncConversation. It receives a DisconnectionDetails with a reason of "user", "agent" or "error", plus the WebSocket close code and reason when available, and replaces the deprecated callback_end_session. The regenerated client moves client.speech_to_speech to the /v1/voice-changer paths and adds client.environment_variables.delete, client.conversational_ai.tests.invocations.update and the same new parameters as JavaScript SDK v2.75.0.

Android SDK

• v0.13.0 - agent_tool_request is now handled as a notification event instead of a client tool call, so client tools no longer run twice, the first time without parameters. The SDK also no longer crashes when a client tool answers after the connection has closed.

ElevenLabs CLI

• v1.7.1 - say uses eleven_v4 and new agent templates use eleven_v4_turbo by default. Fixes onboard sign-in on Windows and when the token cannot be saved to the keychain.

Packages

• @elevenlabs/client@1.29.0 and @elevenlabs/react@1.19.0 - Added the onAudioAlignmentPlayback callback, called with { event_id, alignment } when an aligned audio chunk starts playing, for syncing text with speech. It is not called on WebRTC connections.
• @elevenlabs/client@1.30.0 - Added the opt-in stripAudioTags session option, which removes audio tags such as [laughs] from agent messages passed to onMessage and onAgentResponseCorrection, and exports the stripAudioTags helper. Stripped text no longer lines up with onAudioAlignment timings.
• @elevenlabs/client@1.31.0, @elevenlabs/types@0.26.0 and @elevenlabs/react@1.20.0 - Added overrides.tts.modelId for a per-conversation TTS model override. Realtime Speech to Text emits RealtimeEvents.AUDIO_STARTED once the first microphone audio frame is sent, and useScribe in microphone mode reports connected only from that point.
• @elevenlabs/convai-widget-core@0.21.0 and @elevenlabs/convai-widget-embed@0.21.0 - Voice call transcripts are revealed in step with the agent’s speech, and an interrupted reply keeps only what was said. Resuming a persistent text conversation no longer asks the user to accept the terms again.
• @elevenlabs/convai-widget-core@0.21.1, 0.21.3 and 0.21.4 - Text chat shows typing dots while the agent prepares its reply. Rich content carousels show a page indicator, stay clickable after the conversation moves on, and appear in voice calls while the agent is still speaking. On screens narrower than 768px the chat opens fullscreen; add mobile-fullscreen="false" to the embed to keep the compact layout.
• @elevenlabs/react-native@1.2.31, 1.2.32 and 1.2.33 - Updated to the latest @elevenlabs/client and @elevenlabs/react releases.

New endpoints

ElevenAgents

• DELETE /v1/convai/environment-variables/{env_var_id} - Delete an environment variable. Returns 204.
• PATCH /v1/convai/test-invocations/{test_invocation_id} - Rename a test invocation with required name (string, 1 to 256 characters, or null to restore the generated title).

Voice Changer

• Voice changer - POST /v1/voice-changer/{voice_id} and Voice changer stream - POST /v1/voice-changer/{voice_id}/stream - The documented paths for Voice Changer. POST /v1/speech-to-speech/{voice_id} and POST /v1/speech-to-speech/{voice_id}/stream are removed from the API reference and deprecated.

Updated endpoints

ElevenAgents

• Create agent, Get agent and Update agent
  • Prompt configuration adds service_tier (standard or fast, default standard). Workflow node prompt overrides add nullable service_tier.
  • Widget configuration adds mobile_fullscreen (boolean, default true).
• List LLMs - Each model adds required available_service_tiers (array of standard or fast).
• Calculate LLM usage and Calculate expected LLM usage for an agent - Added optional service_tier.
• Get widget - Widget configuration adds mobile_fullscreen (boolean, default true).
• Create crawl job - Added optional exclude_patterns (array of strings, up to 50 items of up to 2,048 characters each).
• Get crawl job and List crawl jobs - Crawl jobs add exclude_patterns (array of strings).
• Knowledge base document responses - auto_sync_info removes the deprecated auto_discover field.
• Run tests - Added optional name (string, 1 to 256 characters). Get test invocation and List test invocations return nullable name.
• Update branch - Added optional description (string, up to 4,096 characters). Pass an empty string to clear it.
• Get conversation details
  • Conversation charging adds nullable voice_surcharge_charge (integer).
  • Agent definition source enum adds architect.
• Agent deployments (GET /v1/convai/agents/{agent_id}/deployments) - Deployment source enum adds duplicate.
• Conversation initiation client data, including the conversation_initiation_client_data WebSocket event and Submit batch call - Added optional start_procedure_ids (array of strings).
• Tool type enum removes api_integration_mcp.

Text to Speech and Text to Dialogue

• Create dialogue, Stream dialogue and their timestamp variants - use_pvc_as_ivc is deprecated.
• Text to Speech voice_settings and Text to Dialogue settings - Added nullable clone_strength (number, 0 to 1). Get voice settings, Get voice and List voices return it.

Dubbing

• List dubs, Dub a video or an audio file, GET /v1/dubbing/{dubbing_id}, DELETE /v1/dubbing/{dubbing_id}, GET /v1/dubbing/{dubbing_id}/audio/{language_code} and GET /v1/dubbing/{dubbing_id}/transcripts/{language_code}/format/{format_type} - Marked deprecated.

Workspaces

• Create service account API key - Added optional expires_at_unix (integer or null).
• Update service account API key - Added optional expires_at_unix (integer, or "clear" to remove the expiry; omit to leave it unchanged).
• List service accounts and List service account API keys - API keys add nullable expires_at_unix (integer).

New endpoints

ElevenAgents

• Create realtime client secret - POST /v1/convai/realtime/client_secrets - Create an ephemeral client secret for browser-based Realtime API sessions. Accepts an optional session (OpenAI-compatible session configuration with model of eleven_realtime_v1_mini (default) or eleven_realtime_v1_max, instructions, audio, tools, turn_detection and max_duration_seconds from 60 to 7,200, default 600) and optional expires_after with required seconds (integer). Returns value (string), expires_at (integer) and the echoed session.

• List environments - GET /v1/convai/environments - List the workspace environments, including production. Each environment has name, nullable updated_at_unix_secs and nullable created_by_user_id.

• Create environment - POST /v1/convai/environments - Create an environment with a required, unique name (string). Returns 409 if the name is taken.

• Delete environment - DELETE /v1/convai/environments/{environment} - Delete an environment and remove its values from all environment variables. Returns 204.

Workspaces

• Disable service account API key - POST /v1/service-accounts/{service_account_user_id}/api-keys/{api_key_id}/disable - Disable a service account API key without changing its other settings.

Updated endpoints

ElevenAgents

• Get agent, Update agent, Preview rebase and Preview merge
  • Added optional include_procedure_generated_workflow_elements (boolean, default true). When false, the returned workflow contains only authored nodes and edges, without those generated from structured procedures.
• Create agent, Get agent and Update agent
  • The llm enum adds gemini-4-argon, claude-opus-4-6 and nemotron-35-super-vl-nvfp4.
  • TTS configuration effects removes the deprecated seed field.
• Delete agent - Added optional force (boolean, default false).
• List agents - sort_by adds updated_at. Agent summaries add required updated_at_unix_secs (integer).
• Rebase branch and Preview rebase - Added optional source_branch_id (string). Defaults to the agent’s main branch.
• Outbound call, Submit batch call and Get batch call
  • Twilio machine detection configuration adds actions, an array of rules with required action (hang_up) and required answered_by (array of human, fax, unknown, machine_start, machine_end_beep, machine_end_silence or machine_end_other). Each action can appear in at most one rule.
• Get conversation details
  • Transcript tool calls add nullable tool_id (string). It is not set for tools without an ID, such as system tools.
  • Turn metrics add nullable voice_id (string).
  • Tool results add nullable to_agent and to_node (string).
  • WhatsApp conversation info adds nullable recipient with nullable phone and bsuid (string), and nullable call_permission_request with required state (blocked, sent, accepted or declined) and nullable requested_at_unix (integer).
  • The platform charge category enum adds v3_addon, v4_addon and rag_addon.
• Get ticket, List tickets and List workspace tickets
  • Ticket responses add required status_changes, an array of objects with status, nullable changed_by_user_id (string) and changed_at_unix_secs (integer).

Text to Speech and Text to Dialogue

• Create speech, Stream speech, Create dialogue and Stream dialogue, including their timestamp variants - use_pvc_as_ivc is now nullable and no longer declares a default of false.

Music

• Compose music, Compose detailed, Stream music, Compose detailed stream, Separate stems, Video to music and POST /v1/music/plan
  • Added optional enable_logging query parameter (boolean, default true). Set it to false for Zero Retention Mode.
• Video to music - Added optional add_sfx, separate_tracks and use_audio_as_reference (boolean, default false).

Sound Effects

• Create sound effect
  • Added optional enable_logging query parameter (boolean, default true).
  • output_format adds wav_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100 and wav_48000.

Speech Engine

• List Speech Engines - sort_by adds updated_at. Summaries add required updated_at_unix_secs (integer).

Speech to Text

• Create transcript and Get transcript - Edited transcripts add required, read-only edited_text (string), matching text and the edited_text field of the realtime edited_transcript event.

Dubbing

• GET /v1/dubbing/project/{project_id}/language and GET /v1/dubbing/project/{project_id}/language/{language_id} - Language outputs add nullable subtitles (string, signed URL).

Voices

• Get voice, List voices and Get voices - Voice sharing review_status adds declined_resubmittable.

Workspaces

• List workspace groups and List service accounts
  • Groups add nullable group_concurrency_limit, group_dubbing_concurrency_limit and group_music_concurrency_limit (integer or unlimited).
  • Group permissions add all_resources_access.

New endpoints

ElevenAgents

• Merge tickets - POST /v1/convai/triage-tickets/{agentqa_ticket_id}/merge - Merge open tickets into the target ticket. Requires source_ticket_ids (string array, 1–50 items) and returns the target ticket.

Voices

• List voice collections - GET /v1/voices/collections - List the voice collections the caller can access, sorted by title.
• Create voice collection - POST /v1/voices/collections - Create a collection with required title and icon (string, maximum 1,000 characters each).
• Get voice collection - GET /v1/voices/collections/{collection_id} - Retrieve a collection with its title, icon and the caller’s permission_on_resource (admin, editor, commenter or viewer).
• Update voice collection - PATCH /v1/voices/collections/{collection_id} - Update the optional title or icon.
• Delete voice collection - DELETE /v1/voices/collections/{collection_id}
• Add voice to collection - POST /v1/voices/collections/{collection_id}/voice/{voice_id}
• Remove voice from collection - DELETE /v1/voices/collections/{collection_id}/voice/{voice_id}

Audio effects

• GET /v1/audio-effects/catalog - List the available filter_presets, environments and background_noises. Each entry has an ID, a name and a nullable description.

Updated endpoints

ElevenAgents

• Create agent, Get agent and Update agent
  • Workflow End nodes add outcome (success or failure, default success). The field is required in responses.
  • Standalone workflow agent nodes and agent transfer configurations add nullable branch_id (string) to target a specific branch of the destination agent. When unset, the transfer follows the target agent’s traffic deployment. Transfer tool results add a configured branch reason.
  • Prompt override configurations add tool_ids_strict (boolean, default false).
  • TTS configuration effects add pan (number, -1 to 1, default 0). The seed field is deprecated and has no effect.
• Get widget config - Added end_confirmation_enabled (boolean, default false).
• List tickets
  • Added optional search (string, maximum 200 characters) and merged_into_ticket_id (string) query parameters.
  • Ticket responses add nullable merged_into_ticket_id and nullable search_match with field (title, description, comment or turn_comment), snippet, highlight_start, highlight_end and nullable turn_index.
• List workspace tickets - Added optional agent_id, sources, priorities, sort_by (created_at or priority, default created_at), owner_user_id, issue_type, label, merged_into_ticket_id and search query parameters.
• List tests - Added optional created_by_user_id (string). Use @me for the authenticated user.
• List test invocations - Added optional test_id (string), version_id (string), start_time and end_time (integer, Unix seconds, inclusive) query parameters.
• Update agent branch - Added optional auto_rebase (boolean). Branch responses add auto_rebase (boolean, default false).
• Get conversation details
  • Twilio, SIP trunk and Exotel phone call metadata add nullable call_result with answered, voicemail, busy, no_answer and failed values.
  • Batch call metadata adds nullable cold_attempt (integer) and nullable conversation_type (initial, retry, callback or redirect).
  • The conversation error type adds workflow_end_failure.
• Knowledge base auto-sync auto_discover is deprecated and no longer has any effect.

Text to Speech

• Create speech, Stream speech, Create speech with timing and Stream speech with timing
  • Added optional nullable audio_effects with filter_preset_id (string), distance (number, 0–1, default 0), environment_id (string), background_noise_id (string), send_level (number, 0–1, default 1) and pan (number, -1 to 1, default 0).
  • Unknown effect IDs return 404. Stereo effects return 400 for ulaw_*, alaw_* and pcm_* output formats.

Text to Dialogue

• Create dialogue, Stream dialogue, Create dialogue with timestamps and Stream dialogue with timestamps - Added optional nullable audio_effects, matching the Text to Speech endpoints.

Speech to Text

• Realtime Speech to Text
  • The commit_strategy query parameter adds turn_prediction, alongside manual and vad.
  • partial_transcript messages add optional turn_probability (number), sent only for models that predict turns.

Music

• POST /v1/music/video-to-music - Responses add a song-id header with the ID of the generated song.

History

• List generated items - The history item source enum adds VoicePreview.

Workspace and user

• Update member - Added optional allow_downgrade_to_basic_seat (boolean, default false).
• Get user - Added required workspace_id (string).
• Service account API key permissions add voice_collections_read and voice_collections_write.

Nuovi endpoint

ElevenAgents

• Crea una proposta di merge - POST /v1/convai/agents/{agent_id}/merge-proposals - Crea una proposta con i campi obbligatori source_branch_id, target_branch_id e title, oltre a una descrizione facoltativa, ID revisori e ID ticket di triage.
• Elenca proposte di merge - GET /v1/convai/agents/{agent_id}/merge-proposals - Elenca le proposte con filtri per stato, branch di origine, branch di destinazione e testo, oltre alla paginazione tramite cursore.
• Ottieni una proposta di merge - GET /v1/convai/agents/{agent_id}/merge-proposals/{merge_proposal_id} - Recupera una proposta e i dettagli relativi a revisione, commenti ed esito.
• Aggiorna una proposta di merge - PATCH /v1/convai/agents/{agent_id}/merge-proposals/{merge_proposal_id} - Aggiorna titolo, descrizione o revisori richiesti, oppure chiudila senza eseguire il merge.
• Esamina una proposta di merge - POST /v1/convai/agents/{agent_id}/merge-proposals/{merge_proposal_id}/reviews - Invia una decisione approved o changes_requested con un commento facoltativo.
• Commenta una proposta di merge - POST /v1/convai/agents/{agent_id}/merge-proposals/{merge_proposal_id}/comments - Aggiungi un commento Markdown fino a 4.096 caratteri.
• Unisci una proposta di merge - POST /v1/convai/agents/{agent_id}/merge-proposals/{merge_proposal_id}/merge - Unisci il branch di origine e controlla facoltativamente la risoluzione forzata dei conflitti e l’archiviazione del branch di origine.
• Elenca deployment degli agenti - GET /v1/convai/agents/{agent_id}/deployments - Elenca le suddivisioni del traffico correnti e cronologiche dei branch con paginazione basata sulle pagine.
• Annulla un’invocazione di test - POST /v1/convai/test-invocations/{test_invocation_id}/cancel - Annulla un’invocazione di test in esecuzione.

Speech Engine

• Duplica uno Speech Engine - POST /v1/speech-engine/{speech_engine_id}/duplicate - Duplica uno Speech Engine e assegna facoltativamente alla copia un nuovo name.

Endpoint aggiornati

ElevenAgents

• Crea agente, Ottieni agente e Aggiorna agente
  • Aggiunti gpt-6.1-sol e claude-sonnet-5-5 all’enum LLM.
  • Aggiunti eleven_v4 e eleven_v4_turbo alle opzioni del modello TTS conversazionale. Il valore predefinito è passato da eleven_flash_v2 a eleven_v4_turbo.
  • I trasferimenti degli agenti e i nodi degli agenti workflow autonomi aggiungono preserve_voice_settings facoltativo (booleano, valore predefinito false) per mantenere la voce di base, il modello TTS e le impostazioni vocali dopo un trasferimento.
  • Le configurazioni dello strumento per saltare il turno aggiungono wait_timeout_secs facoltativo (numero, valore predefinito -1). Il valore -1 mantiene l’agente in silenzio finché il chiamante non parla.
  • Le configurazioni webhook post-chiamata aggiungono exclude_transcript facoltativo (booleano, valore predefinito false) per omettere le trascrizioni turno per turno dai webhook di trascrizione JSON.
  • Le configurazioni di redazione della cronologia delle conversazioni aggiungono excluded_data_collection_ids facoltativo (array di stringhe, massimo 50) per mantenere i valori estratti selezionati mentre vengono oscurate le relative motivazioni.
  • response_timeout_secs dello strumento client ora accetta -1 per attendere indefinitamente quando expects_response è abilitato.
• Elenca ticket
  • Aggiunto priorities facoltativo (array) con valori low, medium, high e urgent.
  • Aggiunto sort_by con valori created_at e priority; il valore predefinito è created_at.
  • Le risposte dei ticket ora richiedono title, priority nullable e un array priority_changes. Le richieste di creazione e aggiornamento dei ticket possono impostare priority e lo stato del ticket aggiunge cancelled.
• Elenca strumenti - Aggiunto used_by_agent_id facoltativo e nullable (stringa) per restituire gli strumenti a cui fa riferimento il branch principale di un agente.
• Esporta risultati delle chiamate batch - Aggiunto limit facoltativo e nullable (intero, minimo 1) per esportare solo i primi destinatari come anteprima di colonna.
• Elenca invocazioni di test e Ottieni invocazione di test
  • I riepiloghi delle invocazioni di test aggiungono cancelled_count obbligatorio (intero) e cancelled facoltativo (booleano, valore predefinito false).
  • Lo stato dell’esecuzione di test aggiunge cancelled.
• Ottieni dettagli della conversazione - Le voci della trascrizione aggiungono platform_event facoltativo e nullable con valori user_turn_timeout e skip_turn_wait_elapsed.
• Ottieni metadati della versione dell’agente - Aggiunto merged_authors facoltativo e nullable, un array che descrive le persone che hanno pubblicato modifiche unite nel branch principale.
• Ottieni job di crawling - Rimosso il campo di risposta deprecato max_depth.

Nuovi endpoint

Flows

• Elenca template - GET /v1/flows/templates - Elenca i template pubblicati e le relative versioni eseguibili.
• Ottieni template - GET /v1/flows/templates/{template_id} - Recupera un template e le relative versioni eseguibili.
• Crea esecuzione di un template - POST /v1/flows/templates/{template_id}/runs - Avvia l’esecuzione di un template con valori di input, una versione facoltativa e un webhook facoltativo.
• Elenca esecuzioni di template - GET /v1/flows/templates/{template_id}/runs - Elenca le esecuzioni di template con paginazione tramite cursore e filtro di versione facoltativo.
• Ottieni esecuzione di un template - GET /v1/flows/templates/{template_id}/runs/{run_id} - Recupera l’esecuzione di un template e lo stato del relativo output.

Endpoint aggiornati

Speech to Text

• Converti parlato in testo - POST /v1/speech-to-text
  • Aggiunto transcript_edit facoltativo e nullable (stringa), che accetta un’istruzione di modifica in linguaggio naturale fino a 2.000 caratteri.
  • Le risposte aggiungono edited_transcript facoltativo e nullable. Una modifica riuscita contiene i campi obbligatori kind: "transcript" e text. Una modifica non riuscita contiene i campi obbligatori kind: "error", error_type: "edit_failed" e message.
• Speech to Text in tempo reale accetta transcript_edit (stringa) ed emette eventi edited_transcript con i campi obbligatori text e edited_text.

ElevenAgents

• Crea agente, Ottieni agente e Aggiorna agente
  • Aggiunti gpt-6-sol, gpt-6-luna, glm-52, deepseek-v41-flash, claude-opus-5 e claude-opus-5-5 all’enum LLM.
  • I monitor di avviso aggiungono enabled facoltativo e nullable (booleano) per controllare se un monitor può inviare notifiche.
• Elenca conversazioni e Ricerca testuale
  • data_collection_params e dynamic_variable_params aggiungono gli operatori neq e in. I valori di in usano un delimitatore pipe.
  • evaluation_params accetta success, failure o unknown come valore del risultato.
• Ricerca intelligente - GET /v1/convai/conversations/messages/smart-search
  • Aggiunto branch_id facoltativo e nullable (stringa).
• Elenca invocazioni di test - GET /v1/convai/test-invocations
  • Aggiunto branch_id facoltativo e nullable (stringa).
  • I riepiloghi delle invocazioni di test aggiungono credits_used facoltativo e nullable (intero) e total_price (numero).
• Ottieni invocazione di test - GET /v1/convai/test-invocations/{test_invocation_id}
  • Le singole esecuzioni di test aggiungono credits_used facoltativo e nullable (intero) e charging (ConversationChargingCommonModel).
• Simula conversazione e Simula stream di conversazione
  • Modificato il valore predefinito facoltativo di new_turns_limit da 10,000 a 100 e impostato il valore massimo a 100.
• Crea job di crawling e Ottieni job di crawling
  • Aggiunto auto_discover facoltativo (booleano, valore predefinito false) per seguire i link e aggiungere le pagine appena individuate durante la sincronizzazione automatica. Richiede enable_auto_sync: true.
• Aggiorna documento della knowledge base - POST /v1/convai/knowledge-base/{documentation_id}/refresh
  • AutoSyncInfo aggiunge auto_discover facoltativo (booleano, valore predefinito false) per indicare se gli aggiornamenti eseguono il crawling e aggiungono le pagine appena individuate.
• Elenca strumenti del server MCP - GET /v1/convai/mcp-servers/{mcp_server_id}/tools
  • Le risposte aggiungono tool_approval_statuses facoltativo (array). Ogni elemento contiene tool_id obbligatorio (stringa) e state (up_to_date, needs_review o not_approved), con campi facoltativi relativi alla policy di approvazione e alla definizione approvata.

Text to Dialogue

• Converti testo in dialogo, Trasmetti testo in dialogo, Converti con timestamp e Trasmetti con timestamp
  • Aggiunto use_pvc_as_ivc facoltativo (booleano, valore predefinito false) per usare la versione Instant Voice Clone di una Professional Voice Clone.
  • Aggiunti previous_text e future_text facoltativi e nullable (stringhe, massimo 100 caratteri) e previous_request_ids e next_request_ids (array di stringhe, massimo 3 ID) per la continuità della generazione.
  • L’oggetto settings facoltativo aggiunge similarity nullable (numero, 0–1, valore predefinito 0.75).

Text to Speech

• Converti testo in parlato, Trasmetti testo in parlato, Converti con timestamp e Trasmetti con timestamp
  • Il campo use_pvc_as_ivc esistente non è più deprecato.

Flows

• Crea generazione di immagini, Crea generazione di video e Crea esecuzione di un template
  • Le destinazioni webhook ora richiedono un discriminatore type esplicito (all o ids). I valori predefiniti precedenti sono stati rimossi.

Voice Design

• Crea voce dall’anteprima, Crea anteprime vocali, Progetta una voce e Remixa una voce
  • Aggiunta una risposta 409 quando è già in corso una generazione per l’anteprima. Riprova la richiesta dopo aver ricevuto questa risposta.

Workspace

• Crea chiave API dell’account di servizio - POST /v1/service-accounts/{service_account_user_id}/api-keys
  • Aggiunti tts_concurrency_limit, music_concurrency_limit e dubbing_concurrency_limit facoltativi e nullable (interi) per le chiavi API degli account di servizio Enterprise.
• Aggiorna chiave API dell’account di servizio - PATCH /v1/service-accounts/{service_account_user_id}/api-keys/{api_key_id}
  • Aggiunti tts_concurrency_limit, music_concurrency_limit e dubbing_concurrency_limit facoltativi. Ogni campo accetta un intero, clear, no_update o null e il valore predefinito è no_update.

Modelli

• Elenca modelli - GET /v1/models
  • Deprecati i campi obbligatori max_characters_request_free_user e max_characters_request_subscribed_user. Questi campi non vengono applicati; usa invece maximum_text_length_per_request.

Nuovi endpoint

ElevenAgents

• Elenca pagina dei numeri di telefono - GET /v1/convai/v2/phone-numbers
  • Aggiunti i parametri di paginazione page_size facoltativo (intero, 1–1.000, predefinito 100) e cursor (stringa nullable).
  • Aggiunti i filtri facoltativi search, label, phone_number, provider, supports_outbound, agent_id, branch_id, sort_by e sort_direction. sort_by accetta label o phone_number; sort_direction è predefinito su asc.
  • La risposta contiene phone_numbers obbligatorio (array), next_cursor facoltativo e nullable (stringa) e has_more (booleano, predefinito false).

Endpoint aggiornati

ElevenAgents

• Crea agente, Ottieni agente e Aggiorna agente
  • La configurazione del prompt aggiunge enable_parallel_tool_calls (booleano, predefinito true). Gli override del workflow accettano un booleano nullable.
  • L’enum LLM aggiunge gpt-6-astra, inclusi gli override per l’avvio della conversazione.
  • I notificatori dell’integrazione di avvisi ora usano integration_type per selezionare pagerduty o slack. I notificatori Slack richiedono connection_id e channel_id (stringhe); channel_id accetta da 1 a 64 caratteri.
• Elenca conversazioni e Risolvi riferimento conversazione
  • data_collection_params non accetta più l’operatore missing. Usa un valore vuoto per trovare le conversazioni in cui il campo non è stato raccolto.
  • Un valore vuoto in dynamic_variable_params trova le conversazioni in cui la variabile non è stata impostata.
• Crea Speech Engine, Ottieni Speech Engine e Aggiorna Speech Engine
  • Aggiunto cascade_timeout_seconds (numero, 2–15). Le richieste di creazione sono predefinite su 4, quelle di aggiornamento accettano un valore nullable e le risposte richiedono il campo.

Immagini e video

• Crea generazione di immagini - POST /v1/flows/image
  • Aggiunte varianti della richiesta per gpt-image-2.5-flare e gpt-image-2.5-sunburst.
  • Entrambe le varianti richiedono prompt e model_id, accettano fino a 10 images e aggiungono resolution (1K, 2K o 4K, predefinito 1K).
  • quality accetta low, medium, high, xhigh o max ed è predefinito su high. aspect_ratio accetta auto e 14 rapporti fissi ed è predefinito su 16:9.

Doppiaggio

• Crea progetto di doppiaggio - POST /v1/dubbing/project
  • keyterms multipart accetta campi ripetuti o un singolo array JSON.
  • webhook_ids multipart accetta campi ripetuti, un singolo array JSON o una stringa separata da virgole.
• Ottieni risorsa del workspace, Condividi risorsa del workspace e Annulla condivisione risorsa del workspace
  • WorkspaceResourceType aggiunge dubbing_project.

Knowledge base

• Crea job di crawling - POST /v1/convai/knowledge-base/crawl
  • Deprecato max_depth (intero, predefinito 3). Il campo ora non ha effetto e non presenta più vincoli minimi o massimi.
  • I metadati del job di crawling non richiedono più max_depth.

Utente

• Ottieni utente e Ottieni abbonamento
  • Gli enum delle valute aggiungono gbp.

Modifiche allo schema

Text to Speech

• I messaggi WebSocket audio e final multi-contesto ora definiscono is_final_audio_for_turn come emesso dopo che tutti i byte nel buffer del turno sono stati forniti.

Nuovi endpoint

ElevenAgents

• Carica audio di attesa dell’agente - POST /v1/convai/agents/{agent_id}/hold-audio
  • Accetta hold_audio_file obbligatorio (binario) come dati del form multipart. Il file deve essere MP3 o WAV, fino a 40 MB e 180 secondi.
  • Restituisce agent_id obbligatorio (stringa) e hold_audio (AgentHoldAudioConfig). L’oggetto hold-audio richiede audio_path, audio_url, original_filename (stringhe), duration_secs (numero) e size_bytes (intero).
• Elimina audio di attesa dell’agente - DELETE /v1/convai/agents/{agent_id}/hold-audio
  • Rimuove la clip personalizzata, così i chiamanti in coda sentono il tono di attesa predefinito.
  • Restituisce agent_id obbligatorio (stringa).

Endpoint aggiornati

ElevenAgents

• Crea agente, Ottieni agente e Aggiorna agente
  • Aggiunto platform_settings.queueing_config (AgentQueueingConfig) facoltativo con enabled (booleano, predefinito false) e wait_timeout_seconds (intero, 1–1.800, predefinito 180).
  • Le risposte di configurazione della coda includono hold_audio (AgentHoldAudioConfig) nullable di sola lettura. Le risposte dell’agente includono anche default_hold_audio_url facoltativo (stringa).
• Ottieni conversazione - GET /v1/convai/conversations/{conversation_id}
  • I metadati aggiungono queue_wait_secs facoltativo e nullable (numero). Il tempo in coda è escluso da call_duration_secs e dal tempo fatturato.
• Crea ramo dell’agente - POST /v1/convai/agents/{agent_id}/branches
  • Aggiunto include_draft facoltativo (booleano, predefinito false). Quando è true, un ramo creato dalla punta del ramo include il set di procedure in bozza del chiamante.
• Elenca procedure e gli endpoint per creare, ottenere e gestire le bozze delle procedure
  • Gli elementi dell’elenco aggiungono referenced_tool_ids, referenced_kb_ids, referenced_procedure_ids e referenced_dynamic_variables facoltativi (array di stringhe).
  • Le risposte dell’agente e di anteprima del merge aggiungono procedures facoltativo, una mappa con chiave ID della procedura.
• Elenca invocation di test - GET /v1/convai/test-invocations
  • Aggiunto search facoltativo e nullable (stringa) per filtrare test e cartelle per nome.
• Esegui test sull’agente e Ottieni invocation di test
  • Le risposte di invocation della suite di test e di esecuzione dei test unitari aggiungono version_id facoltativo e nullable (stringa) e ran_against_draft facoltativo (booleano, predefinito false).
  • I riepiloghi delle invocation aggiungono anche runs_diverged_from_version facoltativo (booleano, predefinito false).
• POST /v1/convai/agents/{agent_id}/knowledge-base/rag-query
  • Il body della richiesta aggiunge gli override specifici della query max_documents_length facoltativo e nullable (intero, 1–50.000) e max_retrieved_rag_chunks_count (intero, 1–20).
• Ottieni account WhatsApp - GET /v1/convai/whatsapp-accounts/{phone_number_id}
  • Aggiunto account_type facoltativo (WhatsAppAccountType, predefinito cloud_api). I valori sono cloud_api e coexistence.
• Calcola l’utilizzo LLM previsto - POST /v1/convai/agent/{agent_id}/llm-usage/calculate
  • LLMUsageCalculatorLLMResponseModel aggiunge price_per_message obbligatorio (numero).

Musica

• MusicModelID aggiunge music_v2_5 per POST /v1/music/video-to-music, POST /v1/music/plan, Componi musica, POST /v1/music/detailed, POST /v1/music/detailed/stream, POST /v1/music/stream, POST /v1/music/upload e POST /v1/music/finetunes.
• GenerationChunk.text aumenta maxLength da 6.000 a 6.132 caratteri per POST /v1/music/plan, POST /v1/music, POST /v1/music/detailed, POST /v1/music/detailed/stream, POST /v1/music/stream e POST /v1/music/upload. I nomi delle sezioni possono contenere da 1 a 100 caratteri e i chunk possono contenere fino a 30 righe con 200 caratteri per riga.

Modifiche allo schema

ElevenAgents

• Gli eventi del server in tempo reale aggiungono queue_status. Il relativo queue_status_event.status obbligatorio accetta waiting, admitted o timed_out; timed_out precede il codice di chiusura WebSocket 4300. L’audio di attesa continua ad arrivare come normali eventi audio.
• L’enum LLM aggiunge gemini-3.8-flash, inclusi gli override per l’avvio della conversazione.
• Le union dei risultati degli strumenti di sistema delle conversazioni aggiungono start_procedure_success, start_procedure_error, end_procedure_success e end_procedure_error.
• FeaturesUsageCommonModel aggiunge gli stati delle funzionalità facoltativi freeform_procedure e structured_procedure.

Nuovi endpoint

ElevenAgents

• Elenca ticket del workspace - GET /v1/convai/triage-tickets
  • Elenca i ticket di triage delle conversazioni per tutti gli agenti a cui il chiamante può accedere, ordinati prima per data di creazione più recente.
  • Aggiunti i parametri query facoltativi page_size (numero intero, 1–100, valore predefinito 100), status (AgentConversationTicketStatus), assignee_user_id (stringa o unassigned) e cursor (stringa).
  • Restituisce GetAgentConversationTicketsPageResponseModel.

Endpoint aggiornati

ElevenAgents

• Elenca conversazioni - GET /v1/convai/conversations
  • Aggiunto dynamic_variable_params facoltativo e annullabile (array di stringhe ripetibile). Ogni valore usa name:op:value, dove op è eq, gt, gte, lt o lte.
• Ricerca testuale nei messaggi delle conversazioni - GET /v1/convai/conversations/messages/text-search
  • Aggiunto dynamic_variable_params facoltativo e annullabile (array di stringhe ripetibile) con la stessa sintassi.
• Chiamata Twilio in uscita, Chiamata in uscita tramite trunk SIP, Chiamata Exotel in uscita e Invia chiamate batch
  • telephony_call_config ora usa schemi di input e output separati.
  • Aggiunto twilio_machine_detection facoltativo e annullabile (TwilioMachineDetectionConfig). Il relativo mode accetta enable o detect_message_end e il valore predefinito è enable. L’impostazione viene ignorata per i provider non Twilio e le chiamate in entrata.
• Importa numero di telefono - POST /v1/convai/phone-numbers
  • Aggiunto account_auth_token facoltativo e annullabile (stringa) per le importazioni di chiavi API Twilio, al fine di convalidare le firme dei webhook in entrata.

Modifiche agli schemi

ElevenAgents

• WebhookEventType aggiunge answering_machine_detection.
• AgentBranchSummary aggiunge draft_created_at facoltativo e annullabile (numero intero) e draft_is_behind_tip facoltativo (booleano, valore predefinito false).
• AgentKnowledgeBaseRagChunkResponseModel aggiunge source_url obbligatorio e annullabile (stringa).
• AgentSummaryResponseModel e SpeechEngineSummaryResponse aggiungono voice_id obbligatorio (stringa).
• AnalysisProperty aggiunge name facoltativo e annullabile (stringa) e allowed_values (AllowedValues). Anche LiteralJsonSchemaProperty aggiunge allowed_values. Entrambi deprecano allowed_values_dynamic_variable.
• DataCollectionResultCommonModel aggiunge name facoltativo e annullabile (stringa).
• WorkspaceApiKeyResponseModel aggiunge platform_limits facoltativo e annullabile (PlatformLimits).
• Lo strumento MCP Icon aggiunge theme facoltativo e annullabile (light o dark).
• SMBToolConfig aggiunge le varianti di parametri send_custom_email, create_service_quote_request e create_product_quote_request.
• Gli schemi dei parametri query dei webhook e la configurazione delle chiamate telefoniche ora usano modelli di input e output separati.
• Gli eventi WebSocket agent_response aggiungono attachments facoltativo (array). Ogni elemento richiede url e name (stringhe) e accetta mime_type facoltativo (stringa).

ElevenCreative

• ReferenceVideo.studio_clip ora usa StudioClipLocator invece di StudioClipReference. I campi e il formato wire restano invariati.