telnyx-ai-assistants-c…
AI voice assistants with custom instructions, knowledge bases, and tool integrations.
Create and manage conference calls, queues, and multi-party sessions. Use when building call centers or conferencing applications. This skill provides Ruby SDK examples.
Claude Code
$ npx -y skills add team-telnyx/ai --skill telnyx-voice-conferencing-ruby --agent claude-code
Codex
$ npx skills add team-telnyx/ai --skill telnyx-voice-conferencing-ruby -a codex -y
Cursor
$ npx skills add team-telnyx/ai --skill telnyx-voice-conferencing-ruby -a cursor -y
Gemini CLI
$ npx skills add team-telnyx/ai --skill telnyx-voice-conferencing-ruby -a gemini-cli -y
GitHub Copilot
$ npx skills add team-telnyx/ai --skill telnyx-voice-conferencing-ruby -a github-copilot -y
OpenCode
$ npx skills add team-telnyx/ai --skill telnyx-voice-conferencing-ruby -a opencode -y
Windsurf
$ npx skills add team-telnyx/ai --skill telnyx-voice-conferencing-ruby -a windsurf -y
name: telnyx-voice-conferencing-ruby description: >- Create and manage conference calls, queues, and multi-party sessions. Use when building call centers or conferencing applications. This skill provides Ruby SDK examples. metadata: author: telnyx product: voice-conferencing language: ruby generated_by: telnyx-openapi-pipeline
<!-- Auto-generated from Telnyx OpenAPI specs. Do not edit. -->
gem install telnyx
require "telnyx" client = Telnyx::Client.new( api_key: ENV["TELNYX_API_KEY"], # This is the default and can be omitted public_key: ENV["TELNYX_PUBLIC_KEY"], # Required for client.webhooks.unwrap (webhook verification) )
All examples below assume `client` is already initialized as shown above.
All API calls can fail with network errors, rate limits (429), validation errors (422), or authentication errors (401). Always handle errors in production code:
begin
result = client.messages.send_(to: "+13125550001", from: "+13125550002", text: "Hello")
rescue Telnyx::Errors::APIConnectionError
puts "Network error — check connectivity and retry"
raise
rescue Telnyx::Errors::RateLimitError
# 429: rate limited — wait, then retry the request (bounded exponential backoff)
sleep(1) # Check Retry-After header for actual delay
# ...retry the call here (give up after a few attempts); otherwise re-raise:
raise
rescue Telnyx::Errors::APIStatusError => e
puts "API error #{e.status}: #{e.message}"
if e.status == 422
puts "Validation error — check required fields and formats"
end
raise # A failed request must never look like success to the caller
endCommon error codes: `401` invalid API key, `403` insufficient permissions, `404` resource not found, `422` validation error (check field formats), `429` rate limited (retry with exponential backoff).
Places the call into a queue, where it waits until it is removed or bridged to another leg. Queue behavior is configured through the request body.
`POST /calls/{call_control_id}/actions/enqueue` — Required: `queue_name`
Optional: `client_state` (string), `command_id` (string), `keep_after_hangup` (boolean), `max_size` (integer), `max_wait_time_secs` (integer)
response = client.calls.actions.enqueue("v3:550e8400-e29b-41d4-a716-446655440000_gRU1OGRkYQ", queue_name: "support")
puts(response)Returns: `result` (string)
Removes the call from the queue it is currently waiting in. The call remains active and can be directed with further call commands.
`POST /calls/{call_control_id}/actions/leave_queue`
Optional: `client_state` (string), `command_id` (string)
response = client.calls.actions.leave_queue("v3:550e8400-e29b-41d4-a716-446655440000_gRU1OGRkYQ")
puts(response)Returns: `result` (string)
Lists conferences. Conferences are created on demand, and will expire after all participants have left the conference or after 4 hours regardless of the number of active participants. Conferences are listed in descending order by `expires_at`.
`GET /conferences`
page = client.conferences.list puts(page)
Returns: `connection_id` (string), `created_at` (string), `end_reason` (enum: all_left, ended_via_api, host_left, time_exceeded), `ended_by` (object), `expires_at` (string), `id` (string), `name` (string), `record_type` (enum: conference), `region` (string), `status` (enum: init, in_progress, completed), `updated_at` (string)
Create a conference from an existing call leg using a `call_control_id` and a conference name. Upon creating the conference, the call will be automatically bridged to the conference. Conferences will expire after all participants have left the conference or after 4 hours regardless of the number of active participants.
`POST /conferences` — Required: `call_control_id`, `name`
Optional: `beep_enabled` (enum: always, never, on_enter, on_exit), `client_state` (string), `comfort_noise` (boolean), `command_id` (string), `duration_minutes` (integer), `hold_audio_url` (string), `hold_media_name` (string), `max_participants` (integer), `region` (enum: Australia, Europe, Middle East, US), `start_conference_on_create` (boolean)
conference = client.conferences.create( call_control_id: "v3:MdI91X4lWFEs7IgbBEOT9M4AigoY08M0WWZFISt1Yw2axZ_IiE4pqg", name: "Business" ) puts(conference)
Returns: `connection_id` (string), `created_at` (string), `end_reason` (enum: all_left, ended_via_api, host_left, time_exceeded), `ended_by` (object), `expires_at` (string), `id` (string), `name` (string), `record_type` (enum: conference), `region` (string), `status` (enum: init, in_progress, completed), `updated_at` (string)
Returns a paginated list of participants in the specified conference, with support for filtering.
`GET /conferences/{conference_id}/participants`
page = client.conferences.list_participants("550e8400-e29b-41d4-a716-446655440000")
puts(page)Returns: `call_control_id` (string), `call_leg_id` (string), `conference` (object), `created_at` (string), `end_conference_on_exit` (boolean), `id` (string), `muted` (boolean), `on_hold` (boolean), `record_type` (enum: participant), `soft_end_conference_on_exit` (boolean), `status` (enum: joining, joined, left), `updated_at` (string), `whisper_call_control_ids` (array[string])
Returns the details of an existing conference, including its current status.
`GET /conferences/{id}`
conference = client.conferences.retrieve("550e8400-e29b-41d4-a716-446655440000")
puts(conference)Returns: `connection_id` (string), `created_at` (string), `end_reason` (enum: all_left, ended_via_api, hos
This repo is the one-stop shop for AI Agents and AI-first developers building with Telnyx — everything an agent needs to build production-grade applications and manage its account, from signup to funding.
AI voice assistants with custom instructions, knowledge bases, and tool integrations.
AI voice assistants with custom instructions, knowledge bases, and tool integrations.
AI voice assistants with custom instructions, knowledge bases, and tool integrations.
AI voice assistants with custom instructions, knowledge bases, and tool integrations.
AI voice assistants with custom instructions, knowledge bases, and tool integrations.
AI voice assistants with custom instructions, knowledge bases, and tool integrations.
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.