/telnyx-ai-inference-curl

name: telnyx-ai-inference-curl
description: >-
  Access Telnyx LLM inference APIs, embeddings, and AI analytics for call
  insights and summaries. This skill provides REST API (curl) examples.
metadata:
  author: telnyx
  product: ai-inference
  language: curl
  generated_by: telnyx-openapi-pipeline

<!-- Auto-generated from Telnyx OpenAPI specs. Do not edit. -->

Telnyx Ai Inference - curl

Installation

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

Setup

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:

# Check HTTP status code in response
response=$(curl -s -w "\n%{http_code}" \
  -X POST "https://api.telnyx.com/v2/messages" \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"to": "+13125550001", "from": "+13125550002", "text": "Hello"}')

http_code=$(echo "$response" | tail -1)
body=$(echo "$response" | sed '$d')

case $http_code in
  2*) echo "Success: $body" ;;
  422) echo "Validation error — check required fields and formats" ;;
  429) echo "Rate limited — retry after delay"; sleep 1 ;;
  401) echo "Authentication failed — check TELNYX_API_KEY" ;;
  *)   echo "Error $http_code: $body" ;;
esac

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

• **Pagination:** List endpoints return paginated results. Use `page[number]` and `page[size]` query parameters to navigate pages. Check `meta.total_pages` in the response.

Transcribe speech to text

Transcribe speech to text. This endpoint is consistent with the [OpenAI Transcription API](https://platform.openai.com/docs/api-reference/audio/createTranscription) and may be used with the OpenAI JS or Python SDK.

`POST /ai/audio/transcriptions`

curl \
  -X POST \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -F "file=@/path/to/file" \
  -F "file_url=https://example.com/file.mp3" \
  -F "model=distil-whisper/distil-large-v2" \
  -F "response_format=json" \
  -F "timestamp_granularities[]=segment" \
  -F "language=en-US" \
  -F "model_config={'smart_format': True, 'punctuate': True}" \
  "https://api.telnyx.com/v2/ai/audio/transcriptions"

Returns: `duration` (number), `segments` (array[object]), `text` (string), `words` (array[object])

Create a chat completion

**Deprecated**: Use `POST /v2/ai/openai/chat/completions` instead. Chat with a language model. This endpoint is consistent with the [OpenAI Chat Completions API](https://platform.openai.com/docs/api-reference/chat) and may be used with the OpenAI JS or Python SDK.

`POST /ai/chat/completions` — Required: `messages`

Optional: `api_key_ref` (string), `best_of` (integer), `early_stopping` (boolean), `enable_thinking` (boolean), `frequency_penalty` (number), `guided_choice` (array[string]), `guided_json` (object), `guided_regex` (string), `length_penalty` (number), `logprobs` (boolean), `max_tokens` (integer), `min_p` (number), `model` (string), `n` (number), `presence_penalty` (number), `response_format` (object), `seed` (integer), `stop` (object), `stream` (boolean), `temperature` (number), `tool_choice` (enum: none, auto, required), `tools` (array[object]), `top_logprobs` (integer), `top_p` (number), `use_beam_search` (boolean)

curl \
  -X POST \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "messages": [
    {
      "role": "system",
      "content": "You are a friendly chatbot."
    },
    {
      "role": "user",
      "content": "Hello, world!"
    }
  ]
}' \
  "https://api.telnyx.com/v2/ai/chat/completions"

List conversations

Retrieve a list of all AI conversations configured by the user. Supports [PostgREST-style query parameters](https://postgrest.org/en/stable/api.html#horizontal-filtering-rows) for filtering. Examples are included for the standard metadata fields, but you can filter on any field in the metadata JSON object.

`GET /ai/conversations`

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

Returns: `created_at` (date-time), `id` (uuid), `last_message_at` (date-time), `metadata` (object), `name` (string)

Create a conversation

Create a new AI Conversation.

`POST /ai/conversations`

Optional: `metadata` (object), `name` (string)

curl \
  -X POST \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  "https://api.telnyx.com/v2/ai/conversations"

Returns: `created_at` (date-time), `id` (uuid), `last_message_at` (date-time), `metadata` (object), `name` (string)

Aggregate Conversation Insights

Aggregate conversation insights by specified fields

`GET /ai/conversations/conversation-insights/aggregates`

curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/conversations/conversation-insights/aggregates"

Returns: `record_count` (integer)

Get Insight Template Groups

Get all insight groups

`GET /ai/conversations/insight-groups`

curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/conversations/insight-groups"

Returns: `created_at` (date-time), `description` (string), `id` (uuid), `insights` (array[object]), `name` (string), `webhook` (string)

Create Insight Template Group

Create a new insight group

`POST /ai/conversations/insight-groups` — Required: `name`

Optional: `description` (string), `webhook` (string)

curl \
  -X POST \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "name": "my-resource"
}' \
  "https://api.telnyx.com