telnyx-ai-assistants-c…
AI voice assistants with custom instructions, knowledge bases, and tool integrations.
Advanced call control features including DTMF sending, SIPREC recording, noise suppression, client state, and supervisor controls. This skill provides Ruby SDK examples.
$ npx -y skills add team-telnyx/ai --skill telnyx-voice-advanced-ruby --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/telnyx-voice-advanced-rubyContext preview
The summary Claude sees to decide when to auto-load this skill.
Advanced call control features including DTMF sending, SIPREC recording, noise suppression, client state, and supervisor controls. This skill provides Ruby SDK examples.
name: telnyx-voice-advanced-ruby description: >- Advanced call control features including DTMF sending, SIPREC recording, noise suppression, client state, and supervisor controls. This skill provides Ruby SDK examples. metadata: author: telnyx product: voice-advanced 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 )
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"
rescue Telnyx::Errors::RateLimitError
# 429: rate limited — wait and retry with exponential backoff
sleep(1) # Check Retry-After header for actual delay
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
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).
Add a participant to an existing AI assistant conversation. Use this command to bring an additional call leg into a running AI conversation.
`POST /calls/{call_control_id}/actions/ai_assistant_join` — Required: `conversation_id`, `participant`
Optional: `client_state` (string), `command_id` (string)
response = client.calls.actions.join_ai_assistant(
"call_control_id",
conversation_id: "v3:abc123",
participant: {id: "v3:abc123def456", role: :user}
)
puts(response)Returns: `conversation_id` (uuid), `result` (string)
Updates client state
`PUT /calls/{call_control_id}/actions/client_state_update` — Required: `client_state`
response = client.calls.actions.update_client_state("call_control_id", client_state: "aGF2ZSBhIG5pY2UgZGF5ID1d")
puts(response)Returns: `result` (string)
Start a Conversation Relay session on an active call. Conversation Relay connects the call audio to your WebSocket so your application can exchange realtime messages with the caller while Telnyx handles speech recognition and text-to-speech. Only one AI Assistant or Conversation Relay session can be active on a call at a time.
`POST /calls/{call_control_id}/actions/conversation_relay_start`
Optional: `assistant` (object), `client_state` (string), `command_id` (string), `conversation_relay_dtmf_detection` (boolean), `conversation_relay_settings` (object), `conversation_relay_url` (string), `custom_parameters` (object), `dtmf_detection` (boolean), `greeting` (string), `interruptible` (enum: none, any, speech, dtmf), `interruptible_greeting` (enum: none, any, speech, dtmf), `interruption_settings` (object), `language` (string), `languages` (array[object]), `provider` (string), `structured_provider` (object), `transcription` (object), `transcription_engine` (enum: Google, Telnyx, Deepgram, Azure, xAI, AssemblyAI, Speechmatics, Soniox, A, B), `transcription_engine_config` (object), `tts_provider` (string), `url` (string), `voice` (string), `voice_settings` (object)
response = client.calls.actions.start_conversation_relay("v3:550e8400-e29b-41d4-a716-446655440000_gRU1OGRkYQ")
puts(response)Returns: `conversation_relay_id` (string), `result` (string)
Stop the active Conversation Relay session on a call.
`POST /calls/{call_control_id}/actions/conversation_relay_stop`
Optional: `client_state` (string), `command_id` (string)
response = client.calls.actions.stop_conversation_relay("v3:550e8400-e29b-41d4-a716-446655440000_gRU1OGRkYQ")
puts(response)Returns: `result` (string)
Sends DTMF tones from this leg. DTMF tones will be heard by the other end of the call. **Expected Webhooks:**
There are no webhooks associated with this command.
`POST /calls/{call_control_id}/actions/send_dtmf` — Required: `digits`
Optional: `client_state` (string), `command_id` (string), `duration_millis` (int32)
response = client.calls.actions.send_dtmf("call_control_id", digits: "1www2WABCDw9")
puts(response)Returns: `result` (string)
Start siprec session to configured in SIPREC connector SRS.
**Expected Webhooks:**
`POST /calls/{call_control_id}/actions/siprec_start`
Optional: `client_state` (string), `connector_name` (string), `include_metadata_custom_headers` (boolean), `secure` (boolean), `session_timeout_secs` (integer), `sip_transport` (enum: udp, tcp, tls), `siprec_track` (enum: inbound_track, outbound_track, both_tracks)
response = client.calls.actions.start_siprec("v3:550e8400-e29b-41d4-a716-446655440000_gRU1OGRkYQ")
puts(response)Returns: `result` (string)
Stop SIPREC session. **Expected Webhooks:**
`POST /calls/{call_control_id}/actions/siprec_stop`
Optional: `client_state` (string), `command_id` (string)
response = client.calls.actions.stop_siprec("v3:550e8400-e29b-41d4-a716-446655440000_gRU1OGRkYQ")
puts(response)Returns: `result` (string)
`POST /calls/{call_control_id}/actions/suppression_start`
Optional: `client_state` (string), `command_id` (string), `direction` (enum: inbound, outbound, both), `noise_suppression_engine` (enum:
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.