Telnyx Ai Assistants Curl logo

Telnyx Ai Assistants Curl

Organization
team-telnyx
telnyx-ai-assistants-curl

AI voice assistants with custom instructions, knowledge bases, and tool integrations.

Overview

Publisherteam-telnyx
Repositoryai
Skill nametelnyx-ai-assistants-curl
Stars
217
Forks
21
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by team-telnyx on GitHub. Read the source before you install it.

Installation

Install the Telnyx Ai Assistants Curl AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/team-telnyx/ai.git /tmp/ai
mkdir -p .claude/skills
cp -r /tmp/ai/providers/claude/plugins/telnyx-ai/skills/telnyx-ai-assistants-curl .claude/skills/telnyx-ai-assistants-curl
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Telnyx Ai Assistants Curl in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Telnyx Ai Assistants Curl on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Telnyx Ai Assistants Curl is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Telnyx AI Assistants - curl

Installation

text
# curl is pre-installed on macOS, Linux, and Windows 10+

Setup

bash
export TELNYX_API_KEY="YOUR_API_KEY_HERE"

All examples below use $TELNYX_API_KEY for authentication.

Error Handling

All API calls can fail with network errors, rate limits (429), validation errors (422), or authentication errors (401). Always handle errors in production code:

bash
curl \
  -X POST \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
      "name": "my-resource",
      "instructions": "You are a helpful assistant.",
      "model": "openai/gpt-4o"
  }' \
  "https://api.telnyx.com/v2/ai/assistants"

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).

Important Notes

  • Phone numbers must be in E.164 format (e.g., +13125550001). Include the + prefix and country code. No spaces, dashes, or parentheses.
  • Pagination: List endpoints return paginated results. Use page[number] and page[size] query parameters to navigate pages. Check meta.total_pages in the response.

Reference Use Rules

Do not invent Telnyx parameters, enums, response fields, or webhook fields.

Core Tasks

Create an assistant

Assistant creation is the entrypoint for any AI assistant integration. Agents need the exact creation method and the top-level fields returned by the SDK.

POST /ai/assistants

ParameterTypeRequiredDescription
namestringYes
instructionsstringYesSystem instructions for the assistant.
tagsarray[string]NoTags associated with the assistant.
modelstringNoID of the model to use when external_llm is not set.
toolsarray[object]NoDeprecated for new integrations.
...+23 optional params in references/api-details.md
bash
curl \
  -X POST \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
      "name": "my-resource",
      "instructions": "You are a helpful assistant.",
      "model": "openai/gpt-4o"
  }' \
  "https://api.telnyx.com/v2/ai/assistants"

Primary response fields:

  • .data.id
  • .data.name
  • .data.model
  • .data.instructions
  • .data.created_at
  • .data.conversation_flow

Chat with an assistant

Chat is the primary runtime path. Agents need the exact assistant method and the response content field.

POST /ai/assistants/{assistant_id}/chat

ParameterTypeRequiredDescription
contentstringYesThe message content sent by the client to the assistant
conversation_idstring (UUID)YesA unique identifier for the conversation thread, used to mai...
assistant_idstring (UUID)YesUnique identifier of the assistant.
namestringNoThe optional display name of the user sending the message
bash
curl \
  -X POST \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "content": "Tell me a joke about cats",
  "conversation_id": "42b20469-1215-4a9a-8964-c36f66b406f4"
}' \
  "https://api.telnyx.com/v2/ai/assistants/550e8400-e29b-41d4-a716-446655440000/chat"

Primary response fields:

  • .data.content

Create an assistant test

Test creation is the main validation path for production assistant behavior before deployment.

POST /ai/assistants/tests

ParameterTypeRequiredDescription
namestringYesA descriptive name for the assistant test.
destinationstringYesThe target destination for the test conversation.
instructionsstringYesDetailed instructions that define the test scenario and what...
rubricarray[object]YesEvaluation criteria used to assess the assistant's performan...
descriptionstringNoOptional detailed description of what this test evaluates an...
telnyx_conversation_channelobjectNoThe communication channel through which the test will be con...
max_duration_secondsintegerNoMaximum duration in seconds that the test conversation shoul...
...+1 optional params in references/api-details.md
bash
curl \
  -X POST \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "name": "Customer Support Bot Test",
  "destination": "+15551234567",
  "instructions": "Act as a frustrated customer who received a damaged product. Ask for a refund and escalate if not satisfied with the initial response.",
  "rubric": [
    {
      "criteria": "Assistant responds within 30 seconds",
      "name": "Response Time"
    },
    {
      "criteria": "Provides correct product information",
      "name": "Accuracy"
    }
  ]
}' \
  "https://api.telnyx.com/v2/ai/assistants/tests"

Primary response fields:

  • .data.test_id
  • .data.name
  • .data.destination
  • .data.created_at
  • .data.instructions
  • .data.description

Important Supporting Operations

Use these when the core tasks above are close to your flow, but you need a common variation or follow-up step.

Get an assistant

Fetch the current state before updating, deleting, or making control-flow decisions.

GET /ai/assistants/{assistant_id}

ParameterTypeRequiredDescription
assistant_idstring (UUID)YesUnique identifier of the assistant.
call_control_idstring (UUID)NoFilter results by call control id.
fetch_dynamic_variables_from_webhookbooleanNoWhether to fetch dynamic variables from the configured webho...
fromstring (E.164)NoStart of the filter range.
...+1 optional params in references/api-details.md
bash
curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/assistants/550e8400-e29b-41d4-a716-446655440000"

Primary response fields:

  • .data.id
  • .data.name
  • .data.created_at
  • .data.conversation_flow
  • .data.description
  • .data.dynamic_variables

Update an assistant

Create or provision an additional resource when the core tasks do not cover this flow.

POST /ai/assistants/{assistant_id}

ParameterTypeRequiredDescription
assistant_idstring (UUID)YesUnique identifier of the assistant.
tagsarray[string]NoTags associated with the assistant.
namestringNo
modelstringNoID of the model to use when external_llm is not set.
...+27 optional params in references/api-details.md
bash
curl \
  -X POST \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  "https://api.telnyx.com/v2/ai/assistants/550e8400-e29b-41d4-a716-446655440000"

Primary response fields:

  • .data.id
  • .data.name
  • .data.created_at
  • .data.conversation_flow
  • .data.description
  • .data.dynamic_variables

List assistants

Inspect available resources or choose an existing resource before mutating it.

GET /ai/assistants

bash
curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/assistants"

Response wrapper:

  • items: .data

Primary item fields:

  • id
  • name
  • created_at
  • conversation_flow
  • description
  • dynamic_variables

Import assistants from external provider

Import existing assistants from an external provider instead of creating from scratch.

POST /ai/assistants/import

ParameterTypeRequiredDescription
providerenum (elevenlabs, vapi, retell)YesThe external provider to import assistants from.
api_key_refstringYesIntegration secret pointer that refers to the API key for th...
import_idsarray[string]NoOptional list of assistant IDs to import from the external p...
bash
curl \
  -X POST \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "provider": "elevenlabs",
  "api_key_ref": "my-openai-key"
}' \
  "https://api.telnyx.com/v2/ai/assistants/import"

Response wrapper:

  • items: .data

Primary item fields:

  • id
  • name
  • created_at
  • conversation_flow
  • description
  • dynamic_variables

Get All Tags

Inspect available resources or choose an existing resource before mutating it.

GET /ai/assistants/tags

bash
curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/assistants/tags"

Primary response fields:

  • .data.tags

List assistant tests with pagination

Inspect available resources or choose an existing resource before mutating it.

GET /ai/assistants/tests

ParameterTypeRequiredDescription
test_suitestringNoFilter tests by test suite name
telnyx_conversation_channelstringNoFilter tests by communication channel (e.g., 'web_chat', 'sm...
destinationstringNoFilter tests by destination (phone number, webhook URL, etc....
...+1 optional params in references/api-details.md
bash
curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/assistants/tests"

Response wrapper:

  • items: .data
  • pagination: .meta

Primary item fields:

  • name
  • created_at
  • description
  • destination
  • instructions
  • max_duration_seconds

Get all test suite names

Inspect available resources or choose an existing resource before mutating it.

GET /ai/assistants/tests/test-suites

bash
curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/assistants/tests/test-suites"

Response wrapper:

  • items: .data

Primary item fields:

  • data

Get test suite run history

Fetch the current state before updating, deleting, or making control-flow decisions.

GET /ai/assistants/tests/test-suites/{suite_name}/runs

ParameterTypeRequiredDescription
suite_namestringYesName of the suite.
test_suite_run_idstring (UUID)NoFilter runs by specific suite execution batch ID
statusstringNoFilter runs by execution status (pending, running, completed...
pageobjectNoConsolidated page parameter (deepObject style).
bash
curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/assistants/tests/test-suites/{suite_name}/runs"

Response wrapper:

  • items: .data
  • pagination: .meta

Primary item fields:

  • status
  • created_at
  • updated_at
  • completed_at
  • conversation_id
  • conversation_insights_id

Additional Operations

Use the core tasks above first. The operations below are indexed here with exact SDK methods and required params; use references/api-details.md for full optional params, response schemas, and lower-frequency webhook payloads. Before using any operation below, read the optional-parameters section and the response-schemas section so you do not guess missing fields.

OperationSDK methodEndpointUse whenRequired params
Trigger test suite executionHTTP onlyPOST /ai/assistants/tests/test-suites/{suite_name}/runsTrigger a follow-up action in an existing workflow rather than creating a new top-level resource.suite_name
Get assistant test by IDHTTP onlyGET /ai/assistants/tests/{test_id}Fetch the current state before updating, deleting, or making control-flow decisions.test_id
Update an assistant testHTTP onlyPUT /ai/assistants/tests/{test_id}Modify an existing resource without recreating it.test_id
Delete an assistant testHTTP onlyDELETE /ai/assistants/tests/{test_id}Remove, detach, or clean up an existing resource.test_id
Get test run history for a specific testHTTP onlyGET /ai/assistants/tests/{test_id}/runsFetch the current state before updating, deleting, or making control-flow decisions.test_id
Trigger a manual test runHTTP onlyPOST /ai/assistants/tests/{test_id}/runsTrigger a follow-up action in an existing workflow rather than creating a new top-level resource.test_id
Get specific test run detailsHTTP onlyGET /ai/assistants/tests/{test_id}/runs/{run_id}Fetch the current state before updating, deleting, or making control-flow decisions.test_id, run_id
Delete an assistantHTTP onlyDELETE /ai/assistants/{assistant_id}Remove, detach, or clean up an existing resource.assistant_id
Get Canary DeployHTTP onlyGET /ai/assistants/{assistant_id}/canary-deploysFetch the current state before updating, deleting, or making control-flow decisions.assistant_id
Create Canary DeployHTTP onlyPOST /ai/assistants/{assistant_id}/canary-deploysCreate or provision an additional resource when the core tasks do not cover this flow.assistant_id
Update Canary DeployHTTP onlyPUT /ai/assistants/{assistant_id}/canary-deploysModify an existing resource without recreating it.assistant_id
Delete Canary DeployHTTP onlyDELETE /ai/assistants/{assistant_id}/canary-deploysRemove, detach, or clean up an existing resource.assistant_id
Assistant Sms ChatHTTP onlyPOST /ai/assistants/{assistant_id}/chat/smsRun assistant chat over SMS instead of direct API chat.from, to, assistant_id
Clone AssistantHTTP onlyPOST /ai/assistants/{assistant_id}/cloneTrigger a follow-up action in an existing workflow rather than creating a new top-level resource.assistant_id
Enhance Assistant InstructionsHTTP onlyPOST /ai/assistants/{assistant_id}/instructions/enhanceCreate or provision an additional resource when the core tasks do not cover this flow.assistant_id
List scheduled eventsHTTP onlyGET /ai/assistants/{assistant_id}/scheduled_eventsFetch the current state before updating, deleting, or making control-flow decisions.assistant_id
Create a scheduled eventHTTP onlyPOST /ai/assistants/{assistant_id}/scheduled_eventsCreate or provision an additional resource when the core tasks do not cover this flow.telnyx_conversation_channel, telnyx_end_user_target, telnyx_agent_target, scheduled_at_fixed_datetime, +1 more
Get a scheduled eventHTTP onlyGET /ai/assistants/{assistant_id}/scheduled_events/{event_id}Fetch the current state before updating, deleting, or making control-flow decisions.assistant_id, event_id
Delete a scheduled eventHTTP onlyDELETE /ai/assistants/{assistant_id}/scheduled_events/{event_id}Remove, detach, or clean up an existing resource.assistant_id, event_id
Add Assistant TagHTTP onlyPOST /ai/assistants/{assistant_id}/tagsCreate or provision an additional resource when the core tasks do not cover this flow.tag, assistant_id
Remove Assistant TagHTTP onlyDELETE /ai/assistants/{assistant_id}/tags/{tag}Remove, detach, or clean up an existing resource.assistant_id, tag
Get assistant texmlHTTP onlyGET /ai/assistants/{assistant_id}/texmlFetch the current state before updating, deleting, or making control-flow decisions.assistant_id
Add Assistant ToolHTTP onlyPUT /ai/assistants/{assistant_id}/tools/{tool_id}Modify an existing resource without recreating it.assistant_id, tool_id
Remove Assistant ToolHTTP onlyDELETE /ai/assistants/{assistant_id}/tools/{tool_id}Remove, detach, or clean up an existing resource.assistant_id, tool_id
Test Assistant ToolHTTP onlyPOST /ai/assistants/{assistant_id}/tools/{tool_id}/testTrigger a follow-up action in an existing workflow rather than creating a new top-level resource.assistant_id, tool_id
Get all versions of an assistantHTTP onlyGET /ai/assistants/{assistant_id}/versionsFetch the current state before updating, deleting, or making control-flow decisions.assistant_id
Get a specific assistant versionHTTP onlyGET /ai/assistants/{assistant_id}/versions/{version_id}Fetch the current state before updating, deleting, or making control-flow decisions.assistant_id, version_id
Update a specific assistant versionHTTP onlyPOST /ai/assistants/{assistant_id}/versions/{version_id}Create or provision an additional resource when the core tasks do not cover this flow.assistant_id, version_id
Delete a specific assistant versionHTTP onlyDELETE /ai/assistants/{assistant_id}/versions/{version_id}Remove, detach, or clean up an existing resource.assistant_id, version_id
Promote an assistant version to mainHTTP onlyPOST /ai/assistants/{assistant_id}/versions/{version_id}/promoteTrigger a follow-up action in an existing workflow rather than creating a new top-level resource.assistant_id, version_id
List MCP ServersHTTP onlyGET /ai/mcp_serversInspect available resources or choose an existing resource before mutating it.None
Create MCP ServerHTTP onlyPOST /ai/mcp_serversCreate or provision an additional resource when the core tasks do not cover this flow.name, type, url
Get MCP ServerHTTP onlyGET /ai/mcp_servers/{mcp_server_id}Fetch the current state before updating, deleting, or making control-flow decisions.mcp_server_id
Update MCP ServerHTTP onlyPUT /ai/mcp_servers/{mcp_server_id}Modify an existing resource without recreating it.mcp_server_id
Delete MCP ServerHTTP onlyDELETE /ai/mcp_servers/{mcp_server_id}Remove, detach, or clean up an existing resource.mcp_server_id
List ToolsHTTP onlyGET /ai/toolsInspect available resources or choose an existing resource before mutating it.None
Create ToolHTTP onlyPOST /ai/toolsCreate or provision an additional resource when the core tasks do not cover this flow.type, display_name
Get ToolHTTP onlyGET /ai/tools/{tool_id}Fetch the current state before updating, deleting, or making control-flow decisions.tool_id
Update ToolHTTP onlyPATCH /ai/tools/{tool_id}Modify an existing resource without recreating it.tool_id
Delete ToolHTTP onlyDELETE /ai/tools/{tool_id}Remove, detach, or clean up an existing resource.tool_id

For exhaustive optional parameters, full response schemas, and complete webhook payloads, see references/api-details.md.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Telnyx Ai Assistants Curl AI skill do?

AI voice assistants with custom instructions, knowledge bases, and tool integrations.

Why use Telnyx Ai Assistants Curl on TypingMind?

Because you install it once and use it with any model. Telnyx Ai Assistants Curl is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Telnyx Ai Assistants Curl in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/team-telnyx/ai/tree/main/providers/claude/plugins/telnyx-ai/skills/telnyx-ai-assistants-curl. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Telnyx Ai Assistants Curl?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Telnyx Ai Assistants Curl?

As many as you like. As long as a model supports skills, you can use Telnyx Ai Assistants Curl with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Telnyx Ai Assistants Curl AI skill free?

Yes. It is published on GitHub by team-telnyx under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇