ElevenLabs Speech Engine adds real-time voice to your own chat agent or LLM. ElevenLabs handles speech-to-text, turn-taking, text-to-speech and browser playback while your server owns the agent logic and streams response text over a Speech Engine WebSocket. Use it when you want voice on a custom runtime rather than a fully hosted ElevenAgents configuration.
Build a voice-enabled agent with the Speech Engine SDK in minutes.
Guidance for AI coding assistants integrating Speech Engine.
Create, update and manage Speech Engine resources over the REST API.
text_behavior_overrides, a per-ConversationInitiationSource map of BehaviorOverride objects with optional verbosity, output_format and interaction_budget fields for channel-specific agent behavior.format query parameter. Set format=otlp_traces to return OTLP-compatible trace data alongside the standard conversation payload.ASRConversationalConfigOverride and ASRConversationalConfigOverrideConfig schemas with optional keywords arrays, wired into conversation config client override models.auth_resolved_params (string array) documenting URL placeholders resolved from the auth connection.MusicGenerationMode (track, loop, ambience) and an optional generation_mode field on music prompt request bodies.POST /v1/music/video-to-music) now accepts optional model_id (string, default music_v1).credits_needed_to_convert (integer) indicating credits required before conversion.studio_projects to WorkspaceResourceType.generation_mode, and workspace studio_projects.generation_mode, and workspace studio_projects.AudioContext on the first user gesture and priming the playback graph after the audio worklet loads.strip_audio_tags is off, and treat null top-level terms_html or terms_text as a kill switch for the terms and conditions modal.@elevenlabs/client@1.8.1.GET /v1/convai/conversations/{conversation_id}
format query parameter; otlp_traces returns OTLP-compatible trace datatext_behavior_overrides map keyed by ConversationInitiationSource with BehaviorOverride values (verbosity, output_format, interaction_budget)ConversationInitiationSource enum
intercom_integration, telegram_integration and freshdesk_integrationASRConversationalConfigOverride and ASRConversationalConfigOverrideConfig with optional keywords (array of strings)auth_resolved_params (string array) on webhook configuration modelsPOST /v1/music/video-to-music
model_id (string, default music_v1)generation_mode referencing MusicGenerationMode (track, loop, ambience)credits_needed_to_convert (integer)WorkspaceResourceType enum
studio_projects