> ## Documentation Index > Fetch the complete documentation index at: https://docs.aireserve.com/llms.txt > Use this file to discover all available pages before exploring further. # Mint realtime voice session > Mint a short-lived WebSocket credential for a realtime speech-to-speech session with xAI Grok Voice. Authenticates the caller, checks the `realtimeVoiceEnabled` org gate, resolves voice ownership, reserves worst-case session funds from the wallet, and returns `wss_url` plus an `ephemeral_key`. The key is an HMAC-SHA-256 signed opaque one-use relay ticket (valid 5 minutes); it encodes only expiry and a nonce — the authorized voice is stored in the session record, keyed by the ticket's SHA-256 hash. The relay verifies the HMAC, reads the session record by hash, and injects the authorized voice server-side at WebSocket open; the client cannot change the voice mid-session. Only audio I/O events are accepted; text output, transcription, tools, and session resumption are not supported in this release. ## OpenAPI ````yaml /api-reference/openapi.json post /v1/realtime/sessions openapi: 3.0.3 info: title: AI Reserve Gateway API description: >- The AI Reserve API surface — OpenAI-compatible chat completions, Anthropic-compatible messages, Bedrock Converse, images, video, files, text-to-speech, realtime voice sessions, and GPU Compute pod/volume management — all behind one endpoint and one API key. version: 1.0.0 servers: - url: https://api.aireserve.com security: - bearerAuth: [] paths: /v1/realtime/sessions: post: tags: - Realtime summary: Mint realtime voice session description: >- Mint a short-lived WebSocket credential for a realtime speech-to-speech session with xAI Grok Voice. Authenticates the caller, checks the `realtimeVoiceEnabled` org gate, resolves voice ownership, reserves worst-case session funds from the wallet, and returns `wss_url` plus an `ephemeral_key`. The key is an HMAC-SHA-256 signed opaque one-use relay ticket (valid 5 minutes); it encodes only expiry and a nonce — the authorized voice is stored in the session record, keyed by the ticket's SHA-256 hash. The relay verifies the HMAC, reads the session record by hash, and injects the authorized voice server-side at WebSocket open; the client cannot change the voice mid-session. Only audio I/O events are accepted; text output, transcription, tools, and session resumption are not supported in this release. requestBody: required: true content: application/json: schema: type: object required: - model - voice properties: model: type: string enum: - grok-voice description: Must be `grok-voice`. voice: type: string description: >- Voice to use for this session. Pass a built-in voice ID (from `GET /v1/voices`) or one of your organization's custom voice IDs. Defaults to `ara` when omitted. Voice is locked at mint and cannot change mid-session. example: model: grok-voice voice: ara responses: '201': description: Session minted. Connect the WebSocket before `expires_at`. content: application/json: schema: $ref: '#/components/schemas/RealtimeSessionResponse' example: session_id: 9c3f1a2b-4d5e-6f7a-8b9c-0d1e2f3a4b5c model: grok-voice voice: ara wss_url: >- wss://voice-relay-uat-abcdefg-ue.a.run.app/v1/realtime?model=grok-voice ephemeral_key: >- v1.1756946700.ABCDEFGHIJKLMNOPQRSTuvwxyz01234.signature_base64url_43chars expires_at: '2026-09-03T21:05:00.000Z' key_ttl_seconds: 300 max_session_seconds: 3540 browser_subprotocols: - openai-beta.realtime-v1 - >- openai-insecure-api-key.v1.1756946700.ABCDEFGHIJKLMNOPQRSTuvwxyz01234.signature_base64url_43chars '402': description: Wallet cannot cover the worst-case session cost. '403': description: >- `realtimeVoiceEnabled` is off, or `customVoicesEnabled` is required for the requested custom voice. '404': description: Custom voice ID not found or owned by another organization. '503': description: Voice relay service is not deployed in this environment. components: schemas: RealtimeSessionResponse: type: object description: >- Realtime session mint response. Use `wss_url` and `ephemeral_key` to open the WebSocket. required: - session_id - model - voice - wss_url - ephemeral_key - expires_at - key_ttl_seconds - max_session_seconds - browser_subprotocols properties: session_id: type: string format: uuid description: Unique session identifier used for billing and logging. model: type: string enum: - grok-voice voice: type: string description: Voice bound to this session (cannot change mid-session). wss_url: type: string description: >- Environment-specific WebSocket URL returned by the session mint; use it verbatim. example: >- wss://voice-relay-uat-abcdefg-ue.a.run.app/v1/realtime?model=grok-voice ephemeral_key: type: string description: >- HMAC-SHA-256 signed opaque one-use relay ticket. Encodes expiry and a random nonce only — voice authorization is stored in the session record keyed by this ticket's SHA-256 hash, not in the token itself. Valid until `expires_at`; consumed on first successful connection (replay rejected). Do not log or share. expires_at: type: string format: date-time description: >- Timestamp after which `ephemeral_key` is rejected. Connect promptly — `key_ttl_seconds` is short by design. key_ttl_seconds: type: integer description: Seconds from mint until `ephemeral_key` expires (300 s / 5 min). max_session_seconds: type: integer description: >- Hard session length ceiling enforced by the relay (3,540 s). Mint a new session to continue. browser_subprotocols: type: array items: type: string description: >- Pass this array verbatim as the WebSocket subprotocols from a browser (browsers cannot set Authorization headers). Server-side callers should use `Authorization: Bearer ` instead. securitySchemes: bearerAuth: type: http scheme: bearer description: >- Your AI Reserve API key (aireserve_api_…) from the API Keys page in the portal (https://portal.aireserve.com/keys). ````