> ## Documentation Index > Fetch the complete documentation index at: https://docs.liveavatar.com/llms.txt > Use this file to discover all available pages before exploring further. # Create Session Token > Create session token for authenticated user ## OpenAPI ````yaml /openapi.json post /v1/sessions/token openapi: 3.1.0 info: title: Live avatar API version: 0.1.0 servers: - url: https://api.liveavatar.com security: [] paths: /v1/sessions/token: post: tags: - Sessions summary: Create Session Token description: Create session token for authenticated user operationId: create_session_token_v1_sessions_token_post requestBody: content: application/json: schema: oneOf: - $ref: '#/components/schemas/FullSDKSessionTokenConfigDataSchema' - $ref: '#/components/schemas/LiteSDKSessionTokenConfigDataSchema' title: Payload required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/Response_SDKSessionTokenSchema_' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - APIKeyHeader: [] - HTTPBearer: [] components: schemas: FullSDKSessionTokenConfigDataSchema: properties: mode: type: string const: FULL title: Mode default: FULL avatar_id: type: string format: uuid title: Avatar Id is_sandbox: type: boolean title: Is Sandbox default: false video_settings: anyOf: - $ref: '#/components/schemas/VideoSettings' - type: 'null' description: Video encoding settings max_session_duration: title: Max Session Duration description: >- Maximum session duration in seconds. Must be <= the configured limit for your subscription tier. type: integer avatar_persona: $ref: '#/components/schemas/AvatarPersonaSchema' interactivity_type: $ref: '#/components/schemas/SessionInteractivityTypeEnum' default: CONVERSATIONAL llm_configuration_id: title: Llm Configuration Id description: Optional custom LLM configuration ID type: string format: uuid demo_llm_config: anyOf: - $ref: '#/components/schemas/DemoLLMConfig' - type: 'null' description: >- Inline LLM keys for the demo path. Server-set from `demo_avatars.meta['llm']`. Never sourced from caller input. dynamic_variables: title: Dynamic Variables description: >- Values for ${var} placeholders in the context's opening_text and prompt. Required keys are derived from the context; extra keys are ignored. At most 50 entries; keys <= 64 chars; values <= 1000 chars. additionalProperties: type: string type: object type: object required: - avatar_id - avatar_persona title: Full Mode LiteSDKSessionTokenConfigDataSchema: properties: mode: type: string const: LITE title: Mode default: LITE avatar_id: type: string format: uuid title: Avatar Id is_sandbox: type: boolean title: Is Sandbox default: false video_settings: anyOf: - $ref: '#/components/schemas/VideoSettings' - type: 'null' description: Video encoding settings max_session_duration: title: Max Session Duration description: >- Maximum session duration in seconds. Must be <= the configured limit for your subscription tier. type: integer livekit_config: anyOf: - $ref: '#/components/schemas/LiveKitConfigSchema' - type: 'null' description: LiveKit config. Allow users to override the livekit config agora_config: anyOf: - $ref: '#/components/schemas/AgoraConfigSchema' - type: 'null' description: Agora config. Allow users to use Agora as the transport layer elevenlabs_agent_config: anyOf: - $ref: '#/components/schemas/ElevenLabsAgentConfigSchema' - type: 'null' description: >- ElevenLabs Agent config. When set, uses ElevenLabs Agent instead of default. openai_realtime_config: anyOf: - $ref: '#/components/schemas/OpenAIRealtimeConfigSchema' - type: 'null' description: >- OpenAI Realtime config. When set, uses OpenAI Realtime API instead of default. gemini_realtime_config: anyOf: - $ref: '#/components/schemas/GeminiRealtimeConfigSchema' - type: 'null' description: >- Gemini Realtime config. When set, uses Gemini Live API instead of default. type: object required: - avatar_id title: Lite Mode Response_SDKSessionTokenSchema_: properties: code: type: integer title: Code default: 100 data: anyOf: - $ref: '#/components/schemas/SDKSessionTokenSchema' - type: 'null' message: title: Message type: string type: object title: Response[SDKSessionTokenSchema] HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError VideoSettings: properties: quality: $ref: '#/components/schemas/VideoQualityEnum' default: high encoding: $ref: '#/components/schemas/VideoEncodingEnum' default: H264 type: object title: VideoSettings description: Video encoding settings for session configuration AvatarPersonaSchema: properties: voice_id: title: Voice Id description: Voice ID. If empty use default avatar voice type: string format: uuid context_id: title: Context Id description: Context ID type: string format: uuid language: type: string title: Language description: Language default: en voice_settings: anyOf: - oneOf: - $ref: '#/components/schemas/ElevenLabsVoiceSettings' - $ref: '#/components/schemas/FishAudioVoiceSettings' discriminator: propertyName: provider mapping: elevenLabs: $ref: '#/components/schemas/ElevenLabsVoiceSettings' fish: $ref: '#/components/schemas/FishAudioVoiceSettings' - type: 'null' title: Voice Settings description: >- Additional voice settings (provider-specific, discriminated by 'provider' field) stt_config: anyOf: - $ref: '#/components/schemas/STTConfigSchema' - type: 'null' description: ASR/STT configuration override type: object title: AvatarPersonaSchema SessionInteractivityTypeEnum: type: string enum: - CONVERSATIONAL - PUSH_TO_TALK title: SessionInteractivityTypeEnum DemoLLMConfig: properties: provider: type: string title: Provider description: Provider tag, informational (e.g. 'anthropic', 'openai') model: type: string title: Model description: Model name passed to the provider SDK base_url: title: Base Url description: Custom API base URL type: string ciphertext_api_key: title: Ciphertext Api Key description: >- Base64-encoded encrypted API key (same scheme as voice.encrypted_api_key) type: string type: object required: - provider - model title: DemoLLMConfig description: |- Inline LLM keys for the demo session path. Stashed on `demo_avatars.meta["llm"]` so demo rows don't FK into the user-owned `llm_configurations` table. The agent runtime consumes `model`, `base_url`, and `ciphertext_api_key` directly via `LLMConfig`. LiveKitConfigSchema: properties: livekit_url: type: string title: Livekit Url livekit_room: type: string title: Livekit Room livekit_client_token: type: string title: Livekit Client Token type: object required: - livekit_url - livekit_room - livekit_client_token title: LiveKitConfigSchema AgoraConfigSchema: properties: agora_app_id: type: string title: Agora App Id agora_token: type: string title: Agora Token agora_channel: type: string title: Agora Channel agora_uid: type: string title: Agora Uid type: object required: - agora_app_id - agora_token - agora_channel - agora_uid title: AgoraConfigSchema ElevenLabsAgentConfigSchema: properties: secret_id: type: string format: uuid title: Secret Id description: Secret ID for ELEVENLABS_API_KEY agent_id: type: string title: Agent Id description: ElevenLabs Agent ID voice_id: title: Voice Id description: >- Optional ElevenLabs voice ID override. When set, sent to the ElevenLabs Agent WebSocket as `conversation_config_override.tts.voice_id`, overriding the agent's default voice for this session. When omitted, the agent's configured default voice is used. See https://elevenlabs.io/docs/eleven-agents/api-reference/eleven-agents/websocket type: string dynamic_variables: title: Dynamic Variables description: >- ElevenLabs Agent dynamic variables injected into prompts and tools. See https://elevenlabs.io/docs/eleven-agents/customization/personalization/dynamic-variables additionalProperties: anyOf: - type: string - type: integer - type: number - type: boolean type: object type: object required: - secret_id - agent_id title: ElevenLabsAgentConfigSchema description: >- Config for ElevenLabs Agent mode in LITE sessions. All fields required when present. OpenAIRealtimeConfigSchema: properties: secret_id: type: string format: uuid title: Secret Id description: Secret ID referencing OPENAI_API_KEY secret context_id: title: Context Id description: Context ID. type: string format: uuid voice: $ref: '#/components/schemas/OpenAIRealtimeVoiceEnum' description: OpenAI Realtime voice default: alloy temperature: type: number maximum: 1.2 minimum: 0.6 title: Temperature description: Sampling temperature default: 0.8 model: type: string title: Model description: OpenAI Realtime model default: gpt-realtime type: object required: - secret_id title: OpenAIRealtimeConfigSchema description: Config for OpenAI Realtime Agent mode in LITE sessions. GeminiRealtimeConfigSchema: properties: secret_id: type: string format: uuid title: Secret Id description: Secret ID referencing GEMINI_API_KEY secret context_id: title: Context Id description: Context ID. type: string format: uuid voice: $ref: '#/components/schemas/GeminiRealtimeVoiceEnum' description: Gemini Realtime voice default: Puck temperature: type: number maximum: 2 minimum: 0 title: Temperature description: Sampling temperature default: 0.8 model: $ref: '#/components/schemas/GeminiRealtimeModelEnum' description: Gemini Realtime model default: gemini-3.1-flash-live-preview type: object required: - secret_id title: GeminiRealtimeConfigSchema description: Config for Gemini Realtime Agent mode in LITE sessions. SDKSessionTokenSchema: properties: session_id: title: Session Id type: string format: uuid session_token: type: string title: Session Token type: object required: - session_id - session_token title: SDKSessionTokenSchema ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: title: Message type: string type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError VideoQualityEnum: type: string enum: - very_high - high - medium - low title: VideoQualityEnum VideoEncodingEnum: type: string enum: - VP8 - H264 title: VideoEncodingEnum ElevenLabsVoiceSettings: properties: provider: type: string const: elevenLabs title: Provider default: elevenLabs speed: type: number maximum: 1.2 minimum: 0.8 title: Speed default: 1 stability: type: number maximum: 1 minimum: 0 title: Stability default: 0.75 similarity_boost: type: number maximum: 1 minimum: 0 title: Similarity Boost default: 0.75 style: type: number maximum: 1 minimum: 0 title: Style default: 0 use_speaker_boost: type: boolean title: Use Speaker Boost default: true model: $ref: '#/components/schemas/ElevenLabsModelEnum' description: >- ElevenLabs TTS model. Options: 'eleven_flash_v2_5' (default, faster) or 'eleven_multilingual_v2' (better quality). default: eleven_flash_v2_5 type: object title: ElevenLabsVoiceSettings description: ElevenLabs-specific voice settings for TTS configuration. FishAudioVoiceSettings: properties: provider: type: string const: fish title: Provider default: fish speed: type: number maximum: 1.2 minimum: 0.8 title: Speed default: 1 model: $ref: '#/components/schemas/FishAudioModelEnum' description: Fish Audio TTS model. default: s2 latency_mode: type: string enum: - normal - balanced title: Latency Mode description: 'Latency mode: ''normal'' (~500ms) or ''balanced'' (~300ms).' default: balanced type: object title: FishAudioVoiceSettings description: Fish Audio-specific voice settings for TTS configuration. STTConfigSchema: properties: provider: $ref: '#/components/schemas/STTProviderEnum' description: STT provider. Auto-selected if not specified. type: object required: - provider title: STTConfigSchema description: User-provided STT configuration for sessions. OpenAIRealtimeVoiceEnum: type: string enum: - alloy - ash - ballad - coral - echo - fable - onyx - nova - shimmer - sage - verse - marin - cedar title: OpenAIRealtimeVoiceEnum GeminiRealtimeVoiceEnum: type: string enum: - Achernar - Achird - Algenib - Algieba - Alnilam - Aoede - Autonoe - Callirrhoe - Charon - Despina - Enceladus - Erinome - Fenrir - Gacrux - Iapetus - Kore - Laomedeia - Leda - Orus - Pulcherrima - Puck - Rasalgethi - Sadachbia - Sadaltager - Schedar - Sulafat - Umbriel - Vindemiatrix - Zephyr - Zubenelgenubi title: GeminiRealtimeVoiceEnum GeminiRealtimeModelEnum: type: string enum: - gemini-2.5-flash-native-audio-preview-12-2025 - gemini-3.1-flash-live-preview title: GeminiRealtimeModelEnum ElevenLabsModelEnum: type: string enum: - eleven_flash_v2_5 - eleven_multilingual_v2 title: ElevenLabsModelEnum FishAudioModelEnum: type: string enum: - s1 - s2 title: FishAudioModelEnum STTProviderEnum: type: string enum: - deepgram - assembly_ai - gladia - elevenlabs title: STTProviderEnum securitySchemes: APIKeyHeader: type: apiKey in: header name: X-API-KEY HTTPBearer: type: http scheme: bearer bearerFormat: JWT ````