> ## Documentation Index > Fetch the complete documentation index at: https://anam.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # create session token > Create a new session token used to initialise Anam client side SDKs ## OpenAPI ````yaml https://api.anam.ai/swagger.json post /v1/auth/session-token openapi: 3.1.0 info: title: Anam AI API version: '1.0' servers: - url: https://api.anam.ai description: Anam API security: - BearerAuth: [] tags: - name: Sessions - name: Avatar Videos - name: Meetings - name: Personas - name: Avatars - name: Voices - name: Pronunciation Dictionaries - name: LLMs - name: Knowledge - name: Tools - name: Share Links - name: Engine paths: /v1/auth/session-token: post: tags: - Sessions summary: create session token description: Create a new session token used to initialise Anam client side SDKs operationId: createSessionToken requestBody: description: > Configuration for the session to be created. Supply `personaConfig.personaId` to use a persona you've already created (stateful), or the set `avatarId`/`voiceId`/`llmId`/`systemPrompt` to configure the persona at run time (ephemeral). The returned token is valid for one hour, or for `expiresInSeconds` when set, and bound to this exact config. Server-side SDKs in a secure context can skip this exchange and start a session directly by calling `POST /v1/engine/session` with their API key and the same configuration in the request body. required: true content: application/json: examples: default: $ref: '#/components/examples/SessionTokenCreate' schema: type: object properties: clientLabel: type: string description: The client label for the session maxSessions: type: integer minimum: 1 maximum: 100 description: >- The most sessions the token can start. Omit it for no limit (the default). Each call to `POST /v1/engine/session` with the token counts, including one that fails, so set `maxSessions: 1` only when your client starts the session once and gets a new token to retry. The Anam JS SDK retries a failed start up to 3 times by default: send `maxSessions: 3`, or set the SDK's `retry.maxAttempts` to 1. Reconnects and ICE restarts within a session don't count. Once the limit is reached, session start returns 401. If the API key has its own limit, the lower of the two applies. example: 1 expiresInSeconds: type: integer minimum: 120 maximum: 3600 default: 3600 description: >- How long the token can start sessions, in seconds, from 120 (2 minutes) to 3600 (1 hour). Omit it for one hour. The token is checked only when a session starts: once it expires, `POST /v1/engine/session` returns 401, but a session it already started keeps running until it ends. Start the session within this time, including any retries your client makes. example: 300 personaConfig: description: >- Persona configuration. An avatar-only config (avatarId without voiceId and without enableAudioPassthrough: true) is only accepted together with a LiveKit, Agora or ElevenLabs Agent integration `environment`; on the default Anam WebRTC transport send an ephemeral config with voiceId and llmId (llmId "CUSTOMER_CLIENT_V1" for a client-side LLM) or set enableAudioPassthrough to true. Otherwise the request fails with 400 `avatar_only_requires_integration`. oneOf: - type: object title: Ephemeral persona properties: name: type: string example: Cara avatarId: type: string example: 071b0286-4cce-4808-bee2-e642f1062de3 avatarModel: type: string example: cara-4 description: >- Avatar model version. `cara-4` is pinned to a stable checkpoint; `cara-4-latest` tracks the newest Cara 4 checkpoint and may change between sessions. `cara-5-latest` is an early-access preview that tracks the newest Cara 5 checkpoint; it is available only to organizations that have been granted it, and other organizations get 403. enum: - cara-3 - cara-4 - cara-4.1-express - cara-4-latest - cara-5-latest voiceId: type: string example: de23e340-1416-4dd8-977d-065a7ca11697 llmId: type: string example: a7cf662c-2ace-4de1-a21e-ef0fbf144bb7 systemPrompt: type: string example: You are a helpful assistant maxSessionLengthSeconds: type: number example: 600 skipGreeting: type: boolean example: false uninterruptibleGreeting: type: boolean description: The user can't interrupt the greeting. example: false initialMessage: type: string nullable: true description: >- What the persona says first. Empty or left out, it greets in its own words. example: Hi there! I'm excited to chat with you today. voiceDetectionOptions: $ref: '#/components/schemas/VoiceDetectionOptions' languageCode: type: string description: >- Supported ISO 639 language code override (including "yue" for Cantonese) for transcription, replaces organisation level settings and multilingual (default) mode. voiceGenerationOptions: description: >- Configuration options for voice generation, plus an optional pronunciation dictionary for this session. allOf: - oneOf: - $ref: >- #/components/schemas/ElevenLabsV1VoiceGenerationOptions - $ref: >- #/components/schemas/ElevenLabsV2VoiceGenerationOptions - $ref: >- #/components/schemas/ElevenLabsV3VoiceGenerationOptions - $ref: >- #/components/schemas/ElevenLabsV4VoiceGenerationOptions - $ref: >- #/components/schemas/CartesiaSonic3VoiceGenerationOptions - $ref: >- #/components/schemas/FishAudioVoiceGenerationOptions - $ref: >- #/components/schemas/SessionPronunciationDictionary directorNotes: type: object description: >- Per-session performance overrides for the avatar. Only applied on Cara 4 and Cara 5 avatars (avatarModel `cara-4`, `cara-4.1-express`, `cara-4-latest` or `cara-5-latest`); if set on a cara-3 avatar they are ignored (silently stripped) and the session proceeds without them. `presetStyle` is mutually exclusive with `customStylePrompt` and `customIdlingStylePrompt`. These work best when the selected voice matches the intended performance. properties: presetStyle: type: string enum: - neutral - happy - warm - playful - supportive - sad - angry - distressed description: >- Built-in performance style for the avatar to follow. Mutually exclusive with customStylePrompt. Works best with a voice that matches the intended performance. example: warm customStylePrompt: type: string maxLength: 2000 description: >- Free-form performance style prompt for the avatar to follow while speaking. Mutually exclusive with presetStyle. Works best with a voice that matches the intended performance. example: >- Warm smile, composed, slightly amused, looking directly at camera expressivity: type: number minimum: 0 maximum: 1 description: >- Controls how closely the avatar follows the selected style or cue. 0 is subtle, 1 follows it most strongly and can become unstable; omit the field to use the default. Works best with a voice that matches the intended performance. example: 0.5 customIdlingStylePrompt: type: string nullable: true maxLength: 2000 description: >- Free-form performance style prompt for the avatar to follow while it isn't speaking, such as listening and pauses. Mutually exclusive with presetStyle; omit it to use the model's default idle behaviour. example: >- Listen attentively, nod slowly, soft relaxed gaze tools: type: array description: >- Runtime tool definitions made available to the persona for this session. Each item is one of a client tool, a server knowledge tool, a server webhook tool, or a system tool. For client and webhook tools, `parameters` (and, for webhook tools, `queryParameters`) is a JSON Schema object the LLM fills at call time; each such object must serialize to 10,000 bytes or less (UTF-8), otherwise the request is rejected. Use `toolIds` instead to reference tools you've pre-created via `/v1/tools` (those are not subject to this inline size limit). items: type: object required: - type - name additionalProperties: true properties: type: type: string enum: - client - server - system description: >- Tool kind. `server` tools additionally set `subtype` (`knowledge` or `webhook`). subtype: type: string enum: - knowledge - rag - webhook description: >- Required when `type` is `server`. `knowledge` searches documents in `config.documentFolderIds` (`rag` is a legacy alias for `knowledge`, kept for backwards compatibility); `webhook` calls an external URL. name: type: string description: Unique tool name the LLM calls. description: type: string maxLength: 1024 config: type: object description: >- Type-specific configuration for a `knowledge` server tool. properties: documentFolderIds: type: array items: type: string format: uuid description: IDs of knowledge folders to search. example: - 67d27a9f-0ce1-4432-848b-8ab2b97f024b topK: type: - integer - 'null' minimum: 1 maximum: 100 description: >- Nested form of the flat `topK` field. The flat value is used when both are set. minScore: type: - number - 'null' minimum: 0 maximum: 1 description: >- Nested form of the flat `minScore` field. The flat value is used when both are set. maxContextTokens: type: - integer - 'null' minimum: 1 maximum: 200000 description: >- Nested form of the flat `maxContextTokens` field. The flat value is used when both are set. neighborChunks: type: - integer - 'null' minimum: 0 maximum: 10 description: >- Nested form of the flat `neighborChunks` field. The flat value is used when both are set. documentFolderIds: type: array items: type: string format: uuid description: >- Legacy flat form of `config.documentFolderIds`, kept for backwards compatibility. If both are set, this flat value is used. topK: type: - integer - 'null' minimum: 1 maximum: 100 description: >- Knowledge tools only. Maximum matching chunks to retrieve. Overrides the engine default. Omit or set null to use the default. Fixed tool configuration, not an LLM argument. example: 5 minScore: type: - number - 'null' minimum: 0 maximum: 1 description: >- Knowledge tools only. Minimum relevance score for retrieved chunks. Zero is valid. Omit or set null to use the default. Fixed tool configuration, not an LLM argument. example: 0.5 maxContextTokens: type: - integer - 'null' minimum: 1 maximum: 200000 description: >- Knowledge tools only. Retrieved content token budget, excluding metadata and prompt formatting. Omit or set null to use the default. Fixed tool configuration, not an LLM argument. example: 4000 neighborChunks: type: - integer - 'null' minimum: 0 maximum: 10 description: >- Knowledge tools only. Chunks to add after each match, plus the chunk before it, for surrounding context. 0 returns matches only. Defaults to 0 when omitted or null. Fixed tool configuration, not an LLM argument. example: 0 parameters: type: object description: >- JSON Schema for the arguments the LLM provides (client and webhook tools). Must serialize to 10,000 bytes or less. example: - type: client name: open_calendar description: Open the calendar UI in the client app. parameters: type: object properties: date: type: string description: Date to jump to, in YYYY-MM-DD format. - type: server subtype: knowledge name: search_docs description: >- Search the knowledge base for relevant documents. config: documentFolderIds: - 67d27a9f-0ce1-4432-848b-8ab2b97f024b toolIds: type: array description: >- IDs of tools pre-created via `/v1/tools` to make available to the persona for this session. items: type: string format: uuid - type: object title: Avatar with audio passthrough description: Avatar-only rendering with audio supplied by the client. required: - avatarId - enableAudioPassthrough properties: avatarId: type: string format: uuid example: 071b0286-4cce-4808-bee2-e642f1062de3 enableAudioPassthrough: type: boolean enum: - true description: >- Must be true; the client supplies audio for the avatar. avatarModel: type: string description: >- Public avatar model version. `cara-5-latest` is an early-access preview that tracks the newest Cara 5 checkpoint; it is available only to organizations that have been granted it, and other organizations get 403. maxSessionLengthSeconds: type: number description: >- Ends the session after this many seconds. Plan limits still apply. example: 1800 directorNotes: type: object nullable: true properties: presetStyle: type: string enum: - neutral - happy - warm - playful - supportive - sad - angry - distressed customStylePrompt: type: string maxLength: 2000 expressivity: type: number minimum: 0 maximum: 1 customIdlingStylePrompt: type: string nullable: true maxLength: 2000 zeroDataRetention: type: boolean enum: - false - type: object title: Saved persona properties: personaId: type: string voiceGenerationOptions: description: >- Only `pronunciationDictionaryId` applies to a saved persona; voice settings come from the persona, and any other keys are ignored. allOf: - $ref: >- #/components/schemas/SessionPronunciationDictionary environment: type: object description: >- Optional engine routing or transport integration environment. The integration type may be supplied explicitly or inferred from the LiveKit, Agora, or ElevenLabs Agent settings. properties: type: type: string enum: - normal - livekit - agora - elevenlabs_agent namespace: type: string minLength: 1 maxLength: 63 pattern: >- ^(?:anam-engine-preview-\d+|devspace-[a-z0-9](?:[a-z0-9-]*[a-z0-9])?)$ podName: type: string engineVersion: type: string livekitUrl: type: string description: >- Must be reachable from the public internet; loopback, private, link-local, reserved, documentation, cluster-internal, and single-label targets are rejected with HTTP 400. Use an absolute URL with an ASCII hostname (punycode for international names), canonical dotted-decimal IPv4, and a port from 1 to 65535 if specified. Hostnames must resolve only to public addresses; DNS is checked when the session starts. Temporary DNS failures are service errors (5xx), not invalid URL errors. livekitToken: type: string agoraSettings: type: object required: - appId - token - channel - uid - quality - videoEncoding - enableStringUids properties: appId: type: string minLength: 1 token: type: string minLength: 1 channel: type: string minLength: 1 uid: type: string minLength: 1 quality: type: string videoEncoding: type: string enableStringUids: type: boolean activityIdleTimeout: type: number audioSampleRate: type: number showAIAvatarDisclosure: type: boolean width: type: integer minimum: 1 height: type: integer minimum: 1 dependentRequired: width: - height height: - width elevenLabsAgentSettings: type: object required: - signedUrl - agentId properties: signedUrl: type: string agentId: type: string conversationConfigOverride: type: object additionalProperties: true dynamicVariables: type: object additionalProperties: true userId: type: string customLlmExtraBody: type: object additionalProperties: true oneOf: - description: >- Default Anam WebRTC transport with optional engine routing. properties: type: type: string enum: - normal not: anyOf: - required: - livekitUrl - required: - livekitToken - required: - agoraSettings - required: - elevenLabsAgentSettings - description: LiveKit transport integration. required: - livekitUrl - livekitToken properties: type: type: string enum: - livekit - description: Agora transport integration. required: - agoraSettings properties: type: type: string enum: - agora - description: ElevenLabs Agent integration. required: - elevenLabsAgentSettings properties: type: type: string enum: - elevenlabs_agent sessionOptions: type: object properties: sessionReplay: type: object deprecated: true description: >- Legacy control for both the recording and the transcript. Use dataRetention instead. It can be sent alongside dataRetention: enableSessionReplay false turns both off, and so does an empty sessionReplay object; enableSessionReplay true leaves each to dataRetention. properties: enableSessionReplay: type: boolean deprecated: true description: >- Record the session and store its transcript. false turns off both, the same as dataRetention with recording and transcripts set to false. Under Zero Data Retention, sending true without dataRetention returns HTTP 400; with dataRetention sent, omitted settings are off and only a dataRetention setting of true that this flag (false, or an empty sessionReplay) does not turn off is rejected. example: true default: true dataRetention: type: object additionalProperties: false description: >- Choose what Anam keeps after the session. Each setting is independent, so you can turn off the recording and keep the transcript, or the other way round. A sessionReplay sent alongside it with enableSessionReplay false, or with no value, turns both off. Zero Data Retention sessions keep neither: an omitted setting is off, and a setting of true returns HTTP 400 unless sessionReplay turns both off. Not supported for LiveKit or Agora sessions (HTTP 400). properties: recording: type: boolean description: >- Record the session video. When false, GET /v1/sessions/{id}/recording returns 404. With sessionOptions.egress mode daily the recording must resolve to off: set this to false, or set enableSessionReplay to false or send an empty sessionReplay. default: true example: false transcripts: type: boolean description: >- Store the conversation transcript. When false, GET /v1/sessions/{id}/transcript returns transcriptsEnabled false and each message reads TRANSCRIPTS_DISABLED. default: true example: true videoQuality: type: string enum: - high - auto description: >- 'high' pins highest bitrate, 'auto' enables adaptive bitrate. example: high showAIAvatarDisclosure: type: boolean description: >- Show the AI avatar disclosure during the session. Defaults to false; set true to opt in. Agora sessions ignore this field. example: true region: type: string enum: - eu - us description: >- Requested engine region. This explicit choice is honored independently of automatic geographic routing. regionPolicy: type: string enum: - preferred - strict default: preferred description: >- `preferred` allows cross-region capacity failover. `strict` keeps the session in the requested region and requires `region`. videoWidth: type: integer description: >- Output video frame width in pixels. Supply together with `videoHeight` (both or neither). Omit to use the avatar model's default. Supported pairs depend on the avatar model — cara-3: `720x480`; cara-4: `1152x768`. Unsupported pairs are rejected (the session is not silently downgraded). example: 1152 videoHeight: type: integer description: >- Output video frame height in pixels. Supply together with `videoWidth` (both or neither). See `videoWidth`. example: 768 egress: type: object description: > Set egress to an alternative egress transport mode. The avatar's audio/video are published to a 3rd party transport and not delivered over the native webRTC channel. The WebRTC peer connection still exists for signalling and the data channel (interrupts, status). Requires `personaConfig.enableAudioPassthrough=true`. Discriminated on `mode`. required: - mode properties: mode: type: string enum: - daily description: Egress provider. Only `daily` is supported today. example: daily daily: type: object description: Required when `mode` is `daily`. required: - roomUrl properties: roomUrl: type: string format: uri description: >- Daily room URL the avatar should join as a publisher. example: https://your-domain.daily.co/avatar-room token: type: string description: >- Optional Daily meeting token. Omit for public rooms. userName: type: string description: >- Optional display name for the avatar participant. Defaults to "anam-avatar". responses: '200': description: Successfully started session content: application/json: schema: $ref: '#/components/schemas/SessionToken' examples: default: $ref: '#/components/examples/SessionTokenResponse' '400': description: >- Invalid request body or incompatible Zero Data Retention configuration. ZDR requests are rejected when the selected voice, LLM or STT provider does not support ZDR, compatibility cannot be verified, dataRetention.recording or dataRetention.transcripts is set to true without a sessionReplay that turns both off, or sessionReplay.enableSessionReplay is set to true without dataRetention. Omitted dataRetention settings are off for ZDR sessions. Region values must be `eu` or `us`, and `regionPolicy: strict` requires an explicit `region`. Avatar-only persona configs (avatarId without voiceId and without enableAudioPassthrough: true) are rejected with `avatar_only_requires_integration` unless a LiveKit, Agora or ElevenLabs Agent integration `environment` is supplied. '401': description: Unauthorized - Invalid or missing API key '403': description: >- Forbidden - API key lacks the required permission, the session config is not authorized for the organization, or the plan does not permit the requested option, including Zero Data Retention or session region selection. content: application/json: schema: type: object required: - error properties: error: type: string message: type: string examples: sessionRegionNotAvailable: value: error: session_region_not_available message: >- Session region selection is not available for this organization '500': description: >- Server error. Note: most errors other than validation and the API key check below are returned as a 500, even though the error might be due to joining the room or related to token validation. '503': description: >- The API key could not be checked because of a temporary server problem (the key may be valid; retry after `Retry-After` seconds), or session storage for the strict region (`region` with `regionPolicy: strict`) is temporarily unavailable, so no token is issued (`error: session_store_unavailable`; retry later). headers: Retry-After: description: >- Seconds to wait before retrying. Present when the API key could not be checked. schema: type: integer content: application/json: schema: $ref: '#/components/schemas/ServiceUnavailableError' examples: sessionStoreUnavailable: value: error: session_store_unavailable message: >- Session storage for this region is temporarily unavailable. Try again later. components: examples: SessionTokenCreate: summary: Mint a token for an ephemeral persona value: personaConfig: name: Cara avatarId: 071b0286-4cce-4808-bee2-e642f1062de3 voiceId: de23e340-1416-4dd8-977d-065a7ca11697 llmId: a7cf662c-2ace-4de1-a21e-ef0fbf144bb7 systemPrompt: You are a helpful assistant. SessionTokenResponse: summary: A freshly minted session token value: sessionToken: >- eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzZXNzaW9uSWQiOiIwMDAwMDAwMC0wMDAwLTAwMDAtMDAwMC0wMDAwMDAwMDAwMDAifQ.signature schemas: VoiceDetectionOptions: type: object description: Options for voice activity detection during user speech input. properties: endOfSpeechSensitivity: type: number description: End-of-speech sensitivity, from 0 (least) to 1 (most sensitive). example: 0.5 minimum: 0 maximum: 1 silenceBeforeSkipTurnSeconds: type: number description: Seconds of silence before the user’s turn is skipped. example: 5 minimum: 0 maximum: 900 silenceBeforeSessionEndSeconds: type: number description: Seconds of silence before the session ends. example: 60 minimum: 0 maximum: 7200 silenceBeforeAutoEndTurnSeconds: type: number description: Seconds of silence before the user’s turn ends. example: 5 minimum: 0.5 maximum: 10 speechEnhancementLevel: type: number description: Speech enhancement, from 0 (none) to 1 (most). example: 0.8 minimum: 0 maximum: 1 sttProvider: type: string enum: - anam - deepgram - cartesia_ink_2 - inworld_stt_1 description: >- Speech-to-text provider to use. Defaults to the platform default when unset. The deepgram provider supports only these languageCode values: en, es, fr, de, hi, ru, pt, ja, it, nl. The cartesia_ink_2 provider supports only these languageCode values: en. The inworld_stt_1 provider supports only these languageCode values: ar, yue, zh, cs, da, nl, en, tl, fi, fr, de, el, hi, hu, id, it, ja, ko, mk, ms, fa, pl, pt, ro, ru, es, sv, th, tr, vi. The inworld_stt_1 provider cannot be used when zeroDataRetention is true. The inworld_stt_1 provider processes audio only in us, so it cannot be used when sessionOptions.regionPolicy is "strict" with any other region. example: anam ElevenLabsV1VoiceGenerationOptions: title: ElevenLabs V1 type: object description: Voice generation options for ElevenLabs V1 models. properties: stability: type: number description: >- Controls how stable the generated voice is between each generation, between 0 (more varied/higher emotional range) and 1 (more stable/less emotional range). example: 0.5 minimum: 0 maximum: 1 similarityBoost: type: number description: >- Controls how close the generated voice is to the original speaker, between 0 (more varied) and 1 (more similar). example: 0 minimum: 0 maximum: 1 speed: type: number description: >- Controls the speed of the spoken voice as a multiplier, between 0.7 (slower) and 1.2 (faster). example: 1 minimum: 0.7 maximum: 1.2 ElevenLabsV2VoiceGenerationOptions: title: ElevenLabs V2 type: object description: Voice generation options for ElevenLabs V2 models. properties: stability: type: number description: >- Controls how stable the generated voice is between each generation, between 0 (more varied/higher emotional range) and 1 (more stable/less emotional range). example: 0.5 minimum: 0 maximum: 1 similarityBoost: type: number description: >- Controls how close the generated voice is to the original speaker, between 0 (more varied) and 1 (more similar). example: 0.75 minimum: 0 maximum: 1 style: type: number description: >- Amplifies the style of the original speaker, between 0 and 1, it is recommended to keep this value low (0) to reduce latency. example: 0 minimum: 0 maximum: 1 useSpeakerBoost: type: boolean description: >- Whether to use speaker boost for the generated voice, enhancing the similarity to the original speaker. example: true speed: type: number description: >- Controls the speed of the spoken voice as a multiplier, between 0.7 (slower) and 1.2 (faster). example: 1 minimum: 0.7 maximum: 1.2 model: $ref: '#/components/schemas/ElevenLabsModelOverride' ElevenLabsV3VoiceGenerationOptions: title: ElevenLabs V3 type: object additionalProperties: false description: >- Voice generation options for an eleven_v3 or eleven_v3_conversational voice, or for any voice whose model override is one of them. Only stability is supported. properties: stability: type: number description: >- Controls how stable the generated voice is, from 0 (more varied) to 1 (more stable). example: 0.5 minimum: 0 maximum: 1 model: $ref: '#/components/schemas/ElevenLabsModelOverride' ElevenLabsV4VoiceGenerationOptions: title: ElevenLabs V4 type: object additionalProperties: false description: >- Voice generation options for an eleven_v4 or eleven_v4_turbo voice, or for any voice whose model override is one of them. Only stability and similarityBoost are supported. properties: stability: type: number description: >- Controls how stable the generated voice is, from 0 (more varied) to 1 (more stable). example: 0.5 minimum: 0 maximum: 1 similarityBoost: type: number description: >- Controls how close the generated voice is to the original speaker, between 0 (more varied) and 1 (more similar). example: 0.75 minimum: 0 maximum: 1 model: $ref: '#/components/schemas/ElevenLabsModelOverride' CartesiaSonic3VoiceGenerationOptions: title: Cartesia Sonic-3 type: object description: Voice generation options for Cartesia Sonic-3 models. properties: volume: type: number description: >- Controls the volume level of the generated voice as a multiplier, between 0.5 (quieter) and 2.0 (louder). example: 1 minimum: 0.5 maximum: 2 speed: type: number description: >- Controls the speed of the spoken voice as a multiplier, between 0.6 (slower) and 1.5 (faster). example: 1 minimum: 0.6 maximum: 1.5 emotion: type: string description: >- Sets the emotional tone of the generated voice. Supported emotions are: neutral, calm, angry, content, sad, scared. example: neutral oneOf: - type: string enum: - neutral - calm - angry - content - sad - scared FishAudioVoiceGenerationOptions: title: Fish Audio type: object description: Voice generation options for Fish Audio models. properties: volume: type: number description: >- Controls the volume level of the generated voice as a multiplier, between 0.5 (quieter) and 2.0 (louder). example: 1 minimum: 0.5 maximum: 2 speed: type: number description: >- Controls the speed of the spoken voice as a multiplier, between 0.5 (slower) and 2.0 (faster). example: 1 minimum: 0.5 maximum: 2 SessionPronunciationDictionary: type: object description: Pronunciation dictionary for this session. properties: pronunciationDictionaryId: type: string format: uuid description: >- ID of a pronunciation dictionary in your organization (create and edit dictionaries in Lab or with the `/v1/pronunciation-dictionaries` endpoints). When the session starts, the dictionary's latest saved entries are applied: the persona speaks each entry's sounds-like replacement, or its IPA pronunciation on voices whose model reads IPA (Cartesia Sonic 3, ElevenLabs v3 and v4), falling back to the entry's optional sounds-like text on other models, while captions and transcripts keep the original words. For a saved persona this replaces the persona's dictionary for this session only; omit it to use the persona's dictionary, if any. An unknown, archived or other-organization ID fails the session when it starts with 404. example: 4f600129-13cf-4bfa-909a-2f4c31467f43 SessionToken: type: object description: >- Short-lived credential used by a client to connect to a live persona. Valid for one hour, or for the `expiresInSeconds` it was created with, and only while that API key stays active. properties: sessionToken: type: string description: >- Signed JWT the client passes to the Anam SDK to open a WebRTC connection. ServiceUnavailableError: type: object required: - error - message properties: error: type: string example: Service temporarily unavailable message: type: string example: We could not check your API key. Please retry shortly. ElevenLabsModelOverride: type: string enum: - eleven_v4_turbo - eleven_v3_conversational - eleven_v4 - eleven_v3 - eleven_flash_v2_5 - eleven_multilingual_v2 - eleven_flash_v2 - eleven_turbo_v2_5 description: >- Replaces the voice's ElevenLabs model for generation. Must be an ElevenLabs model supported for voice imports. The other options must be valid for this model: for example, eleven_v4 accepts only stability and similarityBoost. securitySchemes: BearerAuth: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.