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 Python SDK examples.
$ npx -y skills add team-telnyx/ai --skill telnyx-voice-conferencing-python --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/telnyx-voice-conferencing-pythonContext preview
The summary Claude sees to decide when to auto-load this skill.
Create and manage conference calls, queues, and multi-party sessions. Use when building call centers or conferencing applications. This skill provides Python SDK examples.
name: telnyx-voice-conferencing-python description: >- Create and manage conference calls, queues, and multi-party sessions. Use when building call centers or conferencing applications. This skill provides Python SDK examples. metadata: author: telnyx product: voice-conferencing language: python generated_by: telnyx-openapi-pipeline
<!-- Auto-generated from Telnyx OpenAPI specs. Do not edit. -->
pip install telnyx
import os
from telnyx import Telnyx
client = Telnyx(
api_key=os.environ.get("TELNYX_API_KEY"), # This is the default and can be omitted
)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:
import telnyx
try:
result = client.messages.send(to="+13125550001", from_="+13125550002", text="Hello")
except telnyx.APIConnectionError:
print("Network error — check connectivity and retry")
except telnyx.RateLimitError:
# 429: rate limited — wait and retry with exponential backoff
import time
time.sleep(1) # Check Retry-After header for actual delay
except telnyx.APIStatusError as e:
print(f"API error {e.status_code}: {e.message}")
if e.status_code == 422:
print("Validation error — check required fields and formats")Common 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).
Put the call in a queue.
`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(
call_control_id="550e8400-e29b-41d4-a716-446655440000",
queue_name="support",
)
print(response.data)Returns: `result` (string)
Removes the call from a queue.
`POST /calls/{call_control_id}/actions/leave_queue`
Optional: `client_state` (string), `command_id` (string)
response = client.calls.actions.leave_queue(
call_control_id="550e8400-e29b-41d4-a716-446655440000",
)
print(response.data)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() page = page.data[0] print(page.id)
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",
)
print(conference.data)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)
Lists conference participants
`GET /conferences/{conference_id}/participants`
page = client.conferences.list_participants(
conference_id="550e8400-e29b-41d4-a716-446655440000",
)
page = page.data[0]
print(page.id)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])
Retrieve an existing conference
`GET /conferences/{id}`
conference = client.conferences.retrieve(
id="550e8400-e29b-41d4-a716-446655440000",
)
print(conference.data)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)
End a conference and terminate all active participants.
`POST /conferences/{id}/actions/end`
Optional: `command_id` (string)
response = clie
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.
Repo: team-telnyx/ai
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.