Create session

POST

/live/sessions

Create a Live WebRTC session or place an outbound SIP call. Start with the Live prompting guide for session configuration and Telephony and SIP for trunk setup and call monitoring.

Set transport.type to webrtc and supply an SDP offer, or set it to sip and supply an E.164 destination and trunk credentials. Outbound SIP calling must be enabled for your organization. Ringing is limited to 3 minutes and connected calls to 2 hours; these limits are not configurable in the request.

Returns 201 Created after session initialization. WebRTC responses include an SDP answer. SIP responses do not wait for the callee to answer. Attach a sideband connection using session.id to monitor SIP call progress.

Each SIP request creates a new call. If a request times out or the connection fails, retry with caution: the original request may have succeeded, and a retry can place another call.

Body Parameters
JSON

session: MediaSessionConfig { model, audio, client, 5 more }

Startup configuration for the Live session.

model: string or "gpt-live-1"

The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter.

One of the following:

string

"gpt-live-1"

The Live model. Required in the session configuration for every transport; do not pass it as a URL query parameter.

audio: optional object { output }

Startup audio configuration. WebRTC and SIP negotiate their audio format on the media transport.

output: optional object { voice }

Settings for speech generated by the Live model. Choose the voice before starting the session.

voice: optional string or "alloy" or "ash" or "ballad" or 28 more or CustomVoice { id }

The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to marin and cannot change after startup.

One of the following:

string

"alloy" or "ash" or "ballad" or 28 more

The voice used for Live speech, as a built-in voice name or a custom voice object containing its ID. Defaults to marin and cannot change after startup.

One of the following:

"alloy"

"ash"

"ballad"

"beacon"

"bossa"

"brise"

"cedar"

"cinder"

"coral"

"delta"

"echo"

"flitz"

"gleam"

"harema"

"juni"

"marin"

"meridian"

"nira"

"noeul"

"nuri"

"quartz"

"ripple"

"sage"

"shida"

"shimmer"

"sillage"

"stone"

"tempo"

"verse"

"vesper"

"willow"

CustomVoice object { id }

id: string

minLength1

maxLength128

client: optional ClientConfig { data_channel }

Startup-only capabilities for an untrusted frontend attached to a unified WebRTC session. Trusted sideband connections are unaffected.

data_channel: DataChannelConfig { allowed_client_events, allowed_server_events }

Client and server event permissions for the WebRTC frontend data channel.

allowed_client_events: optional "all" or array of string

Client event types that the frontend data channel may send. Use ‘all’ to allow every client event; an empty array allows none. Omission preserves the existing allow-all behavior.

One of the following:

"all"

array of string

allowed_server_events: optional "all" or array of ServerEventSelector { type, response_event }

Server events that may be sent to the frontend data channel. Use ‘all’ to allow every server event; an empty array allows none. Omission preserves the existing allow-all behavior. Responses events use an object with type ‘response.event’ and a response_event selector.

One of the following:

"all"

array of ServerEventSelector { type, response_event }

type: string

The outer Live server event type. Use ‘response.event’ for Responses events.

minLength1

maxLength256

response_event: optional string

The nested Responses event type. Required when type is ‘response.event’; forbidden for other event types.

minLength1

maxLength256

delegation: optional ClientDelegation { type, acknowledgement_delay_ms } or Responses { responses, type, acknowledgement_delay_ms } or Decisions { decisions, type, acknowledgement_delay_ms } or null

Who handles tasks delegated by the Live model. Omitted or null selects your application; use responses or decisions to delegate to the corresponding API.

One of the following:

ClientDelegation object { type, acknowledgement_delay_ms }

Delegate tasks to your application. The Live session emits delegation events that your backend handles.

type: "client"

The delegation owner. Always client for tasks handled by your application.

acknowledgement_delay_ms: optional number

Milliseconds to wait before requesting an automatic spoken acknowledgement for a delegation. The model may still speak before this delay. Any commentary or thinking appended to the session cancels all pending acknowledgements, including those for other delegations. Defaults to 400 for Decisions sessions and 0 (request immediately) for other sessions. Omission in a session update preserves the current value. Updates apply to subsequent delegations.

minimum0

maximum800

Responses object { responses, type, acknowledgement_delay_ms }

Delegate tasks to a Responses model managed by the Live session.

responses: ResponsesDelegationConfig { model, instructions, max_output_tokens, 6 more }

Backend model, prompt, and tools used when the Live session delegates a task to Responses.

model: string

The model used for server-owned Responses delegations.

instructions: optional string or null

Instructions for the delegated Responses model, separate from Live instructions. See backend prompting.

max_output_tokens: optional number or null

Maximum number of output tokens for each delegated response.

minimum16

parallel_tool_calls: optional boolean or null

Whether the delegated Responses model may request multiple tool calls in a single response.

reasoning: optional object { effort, summary } or null

Reasoning settings passed to each delegated Responses request.

effort: optional "none" or "minimal" or "low" or 3 more or null

How much reasoning effort the delegated Responses model should use. Supported values depend on the backend model.

One of the following:

"none"

"minimal"

"low"

"medium"

"high"

"xhigh"

summary: optional "concise" or "detailed" or "auto" or null

The reasoning summary to request from the delegated Responses model, when supported.

One of the following:

"concise"

"detailed"

"auto"

service_tier: optional "auto" or "default" or "fast_tier_temp_pilot" or 3 more or null

Service tier for delegated Responses requests.

One of the following:

"auto"

"default"

"fast_tier_temp_pilot"

"flex"

"priority"

"ultrafast"

text: optional object { verbosity } or null

Text generation settings passed to each delegated Responses request.

verbosity: optional "low" or "medium" or "high" or null

The amount of detail in text generated by the Responses backend. This does not configure the Live model’s spoken delivery.

One of the following:

"low"

"medium"

"high"

tool_choice: optional "auto" or "none" or "required" or Function { name, type } or Mcp { server_label, type, name } or 11 more

Controls which tool the Responses backend uses when handling a task delegated by the Live model.

One of the following:

LiveToolChoiceEnum = "auto" or "none" or "required"

One of the following:

"auto"

"none"

"required"

Function object { name, type }

The name of the function tool to call.

type: "function"

The tool to call. Always function.

Mcp object { server_label, type, name }

server_label: string

The label of the MCP server to call.

type: "mcp"

The tool to call. Always mcp.

The name of the MCP tool to call. If omitted, the server may choose a default.

FileSearch object { type }

type: "file_search"

The tool to call. Always file_search.

WebSearch object { type }

type: "web_search"

The tool to call. Always web_search.

WebSearchPreview object { type }

type: "web_search_preview"

The tool to call. Always web_search_preview.

ImageGeneration object { type }

type: "image_generation"

The tool to call. Always image_generation.

Computer object { type }

type: "computer"

The tool to call. Always computer.

CodeInterpreter object { type }

type: "code_interpreter"

The tool to call. Always code_interpreter.

ProgrammaticToolCalling object { type }

type: "programmatic_tool_calling"

The tool to call. Always programmatic_tool_calling.

Shell object { type }

Forces the model to call the shell tool when a tool call is required.

type: "shell"

The tool to call. Always shell.

Custom object { name, type }

The name of the custom tool to call.

type: "custom"

The tool to call. Always custom.

ApplyPatch object { type }

Forces the model to call the apply_patch tool when executing a tool call.

type: "apply_patch"

The tool to call. Always apply_patch.

LiveAllowedToolsChoiceParam object { tools, type, mode }

tools: array of Function { name, type } or Mcp { server_label, type, name } or FileSearch { type } or 9 more

The tools that the delegated Responses model may call.

One of the following:

Function object { name, type }

The name of the function tool to call.

type: "function"

The tool to call. Always function.

Mcp object { server_label, type, name }

server_label: string

The label of the MCP server to call.

type: "mcp"

The tool to call. Always mcp.

The name of the MCP tool to call. If omitted, the server may choose a default.

FileSearch object { type }

type: "file_search"

The tool to call. Always file_search.

WebSearch object { type }

type: "web_search"

The tool to call. Always web_search.

WebSearchPreview object { type }

type: "web_search_preview"

The tool to call. Always web_search_preview.

ImageGeneration object { type }

type: "image_generation"

The tool to call. Always image_generation.

Computer object { type }

type: "computer"

The tool to call. Always computer.

CodeInterpreter object { type }

type: "code_interpreter"

The tool to call. Always code_interpreter.

ProgrammaticToolCalling object { type }

type: "programmatic_tool_calling"

The tool to call. Always programmatic_tool_calling.

Shell object { type }

Forces the model to call the shell tool when a tool call is required.

type: "shell"

The tool to call. Always shell.

Custom object { name, type }

The name of the custom tool to call.

type: "custom"

The tool to call. Always custom.

ApplyPatch object { type }

Forces the model to call the apply_patch tool when executing a tool call.

type: "apply_patch"

The tool to call. Always apply_patch.

type: "allowed_tools"

The tool choice type. Always allowed_tools.

mode: optional "none" or "auto" or "required" or null

How to select a tool from the allowed set.

One of the following:

"none"

"auto"

"required"

tools: optional array of FunctionTool { name, type, description, 2 more } or WebSearch { type } or FileSearch { type } or 10 more

Tools available to the Responses backend while it handles tasks delegated by the Live model.

One of the following:

FunctionTool object { name, type, description, 2 more }

A function tool available to the Responses backend when the Live model delegates a task.

The name the delegated Responses model uses when calling this function.

type: "function"

The tool type. Always function.

description: optional string or null

What the function does and when the delegated Responses model should call it.

parameters: optional map[unknown] or null

A JSON Schema object describing the arguments accepted by the function.

strict: optional boolean or null

Whether the delegated Responses model must follow the function’s parameter schema exactly.

WebSearch object { type }

A web search tool available to the Live session’s Responses backend.

type: "web_search"

The tool type. Always web_search.

FileSearch object { type }

type: "file_search"

CodeInterpreter object { type }

type: "code_interpreter"

Shell object { type, environment }

A Responses shell tool. Use a hosted container or return local shell results with response.item.create. Domain secrets are not supported.

type: "shell"

environment: optional ContainerAuto { type, file_ids, memory_limit, 2 more } or ContainerReference { container_id, type } or Local { type, skills } or null

One of the following:

ContainerAuto object { type, file_ids, memory_limit, 2 more }

type: "container_auto"

Automatically creates a container for this request

file_ids: optional array of string or null

An optional list of uploaded files to make available to your code.

memory_limit: optional "1g" or "4g" or "16g" or "64g" or null

The memory limit for the container.

One of the following:

"1g"

"4g"

"16g"

"64g"

network_policy: optional Disabled { type } or Allowlist { allowed_domains, type } or null

Network access policy for the container.

One of the following:

Disabled object { type }

type: "disabled"

Disable outbound network access. Always disabled.

Allowlist object { allowed_domains, type }

allowed_domains: array of string

A list of allowed domains when type is allowlist.

type: "allowlist"

Allow outbound network access only to specified domains. Always allowlist.

skills: optional array of SkillReference { skill_id, type, version } or Inline { description, name, source, type } or null

An optional list of skills referenced by id or inline data.

One of the following:

SkillReference object { skill_id, type, version }

skill_id: string

The ID of the referenced skill.

minLength1

maxLength64

type: "skill_reference"

References a skill created with the /v1/skills endpoint.

version: optional string or null

Optional skill version. Use a positive integer or ‘latest’. Omit for default.

Inline object { description, name, source, type }

description: string

The description of the skill.

The name of the skill.

source: object { data, media_type, type }

Inline skill payload

data: string

Base64-encoded skill zip bundle.

minLength1

maxLength70254592

media_type: "application/zip"

The media type of the inline skill payload. Must be application/zip.

type: "base64"

The type of the inline skill source. Must be base64.

type: "inline"

Defines an inline skill for this request.

ContainerReference object { container_id, type }

container_id: string

The ID of the referenced container.

type: "container_reference"

References a container created with the /v1/containers endpoint

Local object { type, skills }

type: "local"

Use a local computer environment.

skills: optional array of object { description, name, path } or null

An optional list of skills.

description: string

The description of the skill.

The name of the skill.

path: string

The path to the directory containing the skill.

ImageGeneration object { type }

type: "image_generation"

Mcp object { type }

type: "mcp"

Custom object { type }

type: "custom"

Namespace object { type }

type: "namespace"

ToolSearch object { type }

type: "tool_search"

ProgrammaticToolCalling object { type }

type: "programmatic_tool_calling"

Computer object { type }

type: "computer"

ApplyPatch object { type }

type: "apply_patch"

type: "responses"

The delegation owner. Always responses for tasks handled by the Responses API.

acknowledgement_delay_ms: optional number

minimum0

maximum800

Decisions object { decisions, type, acknowledgement_delay_ms }

decisions: DecisionsDelegationConfig { model, questions }

model: string

minLength1

questions: array of Choice { choices, instructions, type, name } or Predicate { instructions, type, name } or Score { instructions, levels, type, name }

Native Decision API questions evaluated together, in order.

One of the following:

Choice object { choices, instructions, type, name }

choices: array of object { value, description }

value: string or boolean

One of the following:

string

boolean

description: optional string

instructions: string

type: "choice"

Predicate object { instructions, type, name }

instructions: string

type: "predicate"

Score object { instructions, levels, type, name }

instructions: string

levels: array of object { label, description }

label: string

description: optional string

type: "score"

type: "decisions"

acknowledgement_delay_ms: optional number

minimum0

maximum800

input: optional array of InitialItem

Ordered text-only history supplied before startup. Supports developer, user, and assistant messages with one text part each; at most 128 messages and a configured rendered-token limit (8,192 by default).

One of the following:

Developer object { content, role, id, 2 more }

A developer message included in the initial text history of a Live session.

content: array of object { text, type }

The message content. Supply exactly one text part for the initial Live conversation history.

text: string

The message text to include in the Live session’s initial conversation history.

type: optional "input_text"

The text content type. Always input_text.

role: "developer"

The author of this history message. Always developer.

id: optional string or null

An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation.

status: optional "incomplete" or "completed" or null

The supplied message’s status. Live uses its text as history and does not resume an incomplete message.

One of the following:

"incomplete"

"completed"

type: optional "message"

The history item type. Always message.

User object { content, role, id, 2 more }

A user message included in the initial text history of a Live session.

content: array of object { text, type }

The message content. Supply exactly one text part for the initial Live conversation history.

text: string

The message text to include in the Live session’s initial conversation history.

type: optional "input_text"

The text content type. Always input_text.

role: "user"

The author of this history message. Always user.

id: optional string or null

An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation.

status: optional "incomplete" or "completed" or null

The supplied message’s status. Live uses its text as history and does not resume an incomplete message.

One of the following:

"incomplete"

"completed"

type: optional "message"

The history item type. Always message.

Assistant object { content, role, id, 2 more }

An assistant message included in the initial text history of a Live session.

content: array of Text { text, type } or OutputText { text, type }

The message content. Supply exactly one text part for the initial Live conversation history.

One of the following:

Text object { text, type }

Assistant text supplied as conversation history when starting a Live session.

text: string

The message text to include in the Live session’s initial conversation history.

type: optional "text"

The text content type. Always text.

OutputText object { text, type }

Assistant output text supplied as conversation history when starting a Live session.

text: string

The message text to include in the Live session’s initial conversation history.

type: "output_text"

The text content type. Always output_text.

role: "assistant"

The author of this history message. Always assistant.

id: optional string or null

An optional identifier for the supplied history message. Live uses the message’s role and text to initialize the conversation.

status: optional "incomplete" or "completed" or null

The supplied message’s status. Live uses its text as history and does not resume an incomplete message.

One of the following:

"incomplete"

"completed"

type: optional "message"

The history item type. Always message.

instructions: optional string or null

Frontend instructions for voice, conversation, interruptions, and when to delegate. Start with the Live prompting guide; put business rules and tool workflows in a separate backend prompt. Limited to 16,384 client-supplied tokens. Omitted or blank instructions use server defaults. Immutable after startup.

store: optional boolean

Whether to store the session for later forking and recording download. Defaults to false for new sessions.

triggers: optional array of DecisionTrigger { decisions, event_type, type }

At most one Decisions trigger per transcript event type. Triggers run independently of delegation. On update, omit triggers to keep the current configuration, send a list to replace it, or send an empty list to disable triggers.

decisions: object { questions }

Questions evaluated using the current transcript and the session’s shared Decision items.

questions: array of Choice { choices, instructions, type, name } or Predicate { instructions, type, name } or Score { instructions, levels, type, name }

Native Decision API questions evaluated together, in order.

One of the following:

Choice object { choices, instructions, type, name }

choices: array of object { value, description }

value: string or boolean

One of the following:

string

boolean

description: optional string

instructions: string

type: "choice"

Predicate object { instructions, type, name }

instructions: string

type: "predicate"

Score object { instructions, levels, type, name }

instructions: string

levels: array of object { label, description }

label: string

description: optional string

type: "score"

event_type: "session.input_transcript.delta" or "session.output_transcript.delta"

One of the following:

"session.input_transcript.delta"

"session.output_transcript.delta"

type: "decisions"

transport: Webrtc { sdp, type } or Sip { destination, trunk, type }

WebRTC transport with an SDP offer, or SIP transport with a destination and per-call trunk credentials.

One of the following:

Webrtc object { sdp, type }

WebRTC transport carrying the offer SDP in a creation request or answer SDP in its response.

sdp: string

Session Description Protocol message for the WebRTC connection.

minLength1

type: "webrtc"

The transport used for the Live session. Always webrtc.

Sip object { destination, trunk, type }

Place an outbound SIP call using your provider’s trunk. Outbound SIP calling must be enabled for your organization. The trunk must support TLS signaling, Opus audio, and SDES-SRTP media. See Telephony and SIP.

destination: string

Phone number to call in E.164 format. SIP URI destinations are not supported.

trunk: object { auth, caller_number, provider_url }

SIP trunk configuration supplied for this call. Keep trunk credentials on your server. The creation response does not return this configuration.

auth: object { password, type, username }

Credentials for SIP Digest authentication with your trunk provider.

password: string

Provider password. Must be at most 4096 bytes and contain no CR, LF, or NUL.

minLength1

type: "digest"

Use digest for SIP Digest authentication. Handles 401 and 407 challenges.

username: string

Provider username. Must contain a non-whitespace character, be at most 256 bytes, and contain no CR, LF, or NUL.

minLength1

caller_number: string

Caller phone number in E.164 format to use in the SIP From header.

provider_url: string

Provider endpoint in the form sips:host[:port][;transport=tcp]. The default port is 5061. IPv6 addresses must be bracketed. TLS signaling is required; plaintext SIP is not supported. Do not include userinfo, a path, URI headers, or other URI parameters. Local hostnames and literal private, loopback, link-local, unspecified, multicast, and broadcast IP addresses are rejected.

type: "sip"

The transport used for the Live session. Always sip.

Returns

session: object { id }

The newly created Live session. Use its ID for session controls and sideband connections.

id: string

Opaque session identifier. Preserve the returned value unchanged, including its prefix.

transport: Webrtc { sdp, type } or Sip { type }

WebRTC transport with an SDP answer, or SIP transport without SDP or trunk credentials. For SIP, attach a sideband using session.id to receive transport.ringing, transport.answered, and transport.failed notifications.

One of the following:

Webrtc object { sdp, type }

WebRTC transport carrying the offer SDP in a creation request or answer SDP in its response.

sdp: string

Session Description Protocol message for the WebRTC connection.

minLength1

type: "webrtc"

The transport used for the Live session. Always webrtc.

Sip object { type }

The SIP transport. Trunk credentials and SDP are not returned.

type: "sip"

The transport used for the Live session. Always sip.

Create session

HTTP

curl https://api.tpg-oai.studydeckedu.com/v1/live/sessions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"session":{"model":"gpt-live-1","instructions":"Be concise. Ask for clarification when needed."},"transport":{"type":"webrtc","sdp":"<SDP offer>"}}'

{"session":{"id":"live_123"},"transport":{"type":"webrtc","sdp":"<SDP answer>"}}

Create session

HTTP

# Export SIP_USERNAME and SIP_PASSWORD in your environment first.
jq -n '{
    "session": {
      "model": "gpt-live-1",
      "instructions": "Help the user schedule an appointment.",
      "audio": { "output": { "voice": "marin" } },
      "delegation": { "type": "client" }
    },
    "transport": {
      "type": "sip",
      "destination": "+14155550123",
      "trunk": {
        "provider_url": "sips:sip.example.com:5061",
        "auth": {
          "type": "digest",
          "username": env.SIP_USERNAME,
          "password": env.SIP_PASSWORD
        },
        "caller_number": "+14155550100"
      }
    }
  }' | curl https://api.tpg-oai.studydeckedu.com/v1/live/sessions \
    -H "Authorization: Bearer $OPENAI_API_KEY" \
    -H "Content-Type: application/json" \
    --data-binary @-

{"session":{"id":"live_123"},"transport":{"type":"sip"}}

Returns Examples

{
  "session": {
    "id": "live_123"
  },
  "transport": {
    "type": "webrtc",
    "sdp": "<SDP answer>"
  }
}

Suggested

Suggested

Create session

Body Parameters
JSON

Returns

Create session

Create session

Returns Examples

Suggested

Create session

Body ParametersJSONExpand Collapse

ReturnsExpand Collapse

Create session

Create session

Returns Examples

Body Parameters
JSON

Returns