telnyx-ai-inference-curl

Name: telnyx-ai-inference-curl
Author: team-telnyx

187stars18forks

How to install telnyx-ai-inference-curl?

team-telnyx/ai/telnyx-ai-inference-curl

$npx -y skills add team-telnyx/ai --skill telnyx-ai-inference-curl

Installs into the current project.

Summary

Access Telnyx LLM inference APIs, embeddings, and AI analytics for call insights and summaries. This skill provides REST API (curl) examples.

Files · 1

View on GitHub

SKILL.md

1	<!-- Auto-generated from Telnyx OpenAPI specs. Do not edit. -->
2
3	# Telnyx Ai Inference - curl
4
5	## Installation
6
7	```text
8	# curl is pre-installed on macOS, Linux, and Windows 10+
9	```
10
11	## Setup
12
13	```bash
14	export TELNYX_API_KEY="YOUR_API_KEY_HERE"
15	```
16
17	All examples below use `$TELNYX_API_KEY` for authentication.
18
19	## Error Handling
20
21	All API calls can fail with network errors, rate limits (429), validation errors (422),
22	or authentication errors (401). Always handle errors in production code:
23
24	```bash
25	# Check HTTP status code in response
26	response=$(curl -s -w "\n%{http_code}" \
27	-X POST "https://api.telnyx.com/v2/messages" \
28	-H "Authorization: Bearer $TELNYX_API_KEY" \
29	-H "Content-Type: application/json" \
30	-d '{"to": "+13125550001", "from": "+13125550002", "text": "Hello"}')
31
32	http_code=$(echo "$response" \| tail -1)
33	body=$(echo "$response" \| sed '$d')
34
35	case $http_code in
36	2*) echo "Success: $body" ;;
37	422) echo "Validation error — check required fields and formats" ;;
38	429) echo "Rate limited — retry after delay"; sleep 1 ;;
39	401) echo "Authentication failed — check TELNYX_API_KEY" ;;
40	*) echo "Error $http_code: $body" ;;
41	esac
42	```
43
44	Common error codes: `401` invalid API key, `403` insufficient permissions,
45	`404` resource not found, `422` validation error (check field formats),
46	`429` rate limited (retry with exponential backoff).
47
48	## Important Notes
49
50	- Pagination: List endpoints return paginated results. Use `page[number]` and `page[size]` query parameters to navigate pages. Check `meta.total_pages` in the response.
51
52	## Transcribe speech to text
53
54	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.
55
56	`POST /ai/audio/transcriptions`
57
58	```bash
59	curl \
60	-X POST \
61	-H "Authorization: Bearer $TELNYX_API_KEY" \
62	-F "file=@/path/to/file" \
63	-F "file_url=https://example.com/file.mp3" \
64	-F "model=distil-whisper/distil-large-v2" \
65	-F "response_format=json" \
66	-F "timestamp_granularities[]=segment" \
67	-F "language=en-US" \
68	-F "model_config={'smart_format': True, 'punctuate': True}" \
69	"https://api.telnyx.com/v2/ai/audio/transcriptions"
70	```
71
72	Returns: `duration` (number), `segments` (array[object]), `text` (string)
73
74	## Create a chat completion
75
76	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.
77
78	`POST /ai/chat/completions` — Required: `messages`
79
80	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), `stream` (boolean), `temperature` (number), `tool_choice` (enum: none, auto, required), `tools` (array[object]), `top_logprobs` (integer), `top_p` (number), `use_beam_search` (boolean)
81
82	```bash
83	curl \
84	-X POST \
85	-H "Authorization: Bearer $TELNYX_API_KEY" \
86	-H "Content-Type: application/json" \
87	-d '{
88	"messages": [
89	{
90	"role": "system",
91	"content": "You are a friendly chatbot."
92	},
93	{
94	"role": "user",
95	"content": "Hello, world!"
96	}
97	]
98	}' \
99	"https://api.telnyx.com/v2/ai/chat/completions"
100	```
101
102	## List conversations
103
104	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.
105
106	`GET /ai/conversations`
107
108	```bash
109	curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/conversations"
110	```
111
112	Returns: `created_at` (date-time), `id` (uuid), `last_message_at` (date-time), `metadata` (object), `name` (string)
113
114	## Create a conversation
115
116	Create a new AI Conversation.
117
118	`POST /ai/conversations`
119
120	Optional: `metadata` (object), `name` (string)
121
122	```bash
123	curl \
124	-X POST \
125	-H "Authorization: Bearer $TELNYX_API_KEY" \
126	-H "Content-Type: application/json" \
127	"https://api.telnyx.com/v2/ai/conversations"
128	```
129
130	Returns: `created_at` (date-time), `id` (uuid), `last_message_at` (date-time), `metadata` (object), `name` (string)
131
132	## Get Insight Template Groups
133
134	Get all insight groups
135
136	`GET /ai/conversations/insight-groups`
137
138	```bash
139	curl -H "Authorization: Bearer $TELNYX_API_KEY

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

telnyx-ai-inference-curl

187stars18forks

View on GitHub

How to install telnyx-ai-inference-curl?

team-telnyx/ai/telnyx-ai-inference-curl

$npx -y skills add team-telnyx/ai --skill telnyx-ai-inference-curl

Installs into the current project.

Summary

Access Telnyx LLM inference APIs, embeddings, and AI analytics for call insights and summaries. This skill provides REST API (curl) examples.

Files · 1

View on GitHub

SKILL.md

1	<!-- Auto-generated from Telnyx OpenAPI specs. Do not edit. -->
2
3	# Telnyx Ai Inference - curl
4
5	## Installation
6
7	```text
8	# curl is pre-installed on macOS, Linux, and Windows 10+
9	```
10
11	## Setup
12
13	```bash
14	export TELNYX_API_KEY="YOUR_API_KEY_HERE"
15	```
16
17	All examples below use `$TELNYX_API_KEY` for authentication.
18
19	## Error Handling
20
21	All API calls can fail with network errors, rate limits (429), validation errors (422),
22	or authentication errors (401). Always handle errors in production code:
23
24	```bash
25	# Check HTTP status code in response
26	response=$(curl -s -w "\n%{http_code}" \
27	-X POST "https://api.telnyx.com/v2/messages" \
28	-H "Authorization: Bearer $TELNYX_API_KEY" \
29	-H "Content-Type: application/json" \
30	-d '{"to": "+13125550001", "from": "+13125550002", "text": "Hello"}')
31
32	http_code=$(echo "$response" \| tail -1)
33	body=$(echo "$response" \| sed '$d')
34
35	case $http_code in
36	2*) echo "Success: $body" ;;
37	422) echo "Validation error — check required fields and formats" ;;
38	429) echo "Rate limited — retry after delay"; sleep 1 ;;
39	401) echo "Authentication failed — check TELNYX_API_KEY" ;;
40	*) echo "Error $http_code: $body" ;;
41	esac
42	```
43
44	Common error codes: `401` invalid API key, `403` insufficient permissions,
45	`404` resource not found, `422` validation error (check field formats),
46	`429` rate limited (retry with exponential backoff).
47
48	## Important Notes
49
50	- Pagination: List endpoints return paginated results. Use `page[number]` and `page[size]` query parameters to navigate pages. Check `meta.total_pages` in the response.
51
52	## Transcribe speech to text
53
54	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.
55
56	`POST /ai/audio/transcriptions`
57
58	```bash
59	curl \
60	-X POST \
61	-H "Authorization: Bearer $TELNYX_API_KEY" \
62	-F "file=@/path/to/file" \
63	-F "file_url=https://example.com/file.mp3" \
64	-F "model=distil-whisper/distil-large-v2" \
65	-F "response_format=json" \
66	-F "timestamp_granularities[]=segment" \
67	-F "language=en-US" \
68	-F "model_config={'smart_format': True, 'punctuate': True}" \
69	"https://api.telnyx.com/v2/ai/audio/transcriptions"
70	```
71
72	Returns: `duration` (number), `segments` (array[object]), `text` (string)
73
74	## Create a chat completion
75
76	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.
77
78	`POST /ai/chat/completions` — Required: `messages`
79
80	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), `stream` (boolean), `temperature` (number), `tool_choice` (enum: none, auto, required), `tools` (array[object]), `top_logprobs` (integer), `top_p` (number), `use_beam_search` (boolean)
81
82	```bash
83	curl \
84	-X POST \
85	-H "Authorization: Bearer $TELNYX_API_KEY" \
86	-H "Content-Type: application/json" \
87	-d '{
88	"messages": [
89	{
90	"role": "system",
91	"content": "You are a friendly chatbot."
92	},
93	{
94	"role": "user",
95	"content": "Hello, world!"
96	}
97	]
98	}' \
99	"https://api.telnyx.com/v2/ai/chat/completions"
100	```
101
102	## List conversations
103
104	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.
105
106	`GET /ai/conversations`
107
108	```bash
109	curl -H "Authorization: Bearer $TELNYX_API_KEY" "https://api.telnyx.com/v2/ai/conversations"
110	```
111
112	Returns: `created_at` (date-time), `id` (uuid), `last_message_at` (date-time), `metadata` (object), `name` (string)
113
114	## Create a conversation
115
116	Create a new AI Conversation.
117
118	`POST /ai/conversations`
119
120	Optional: `metadata` (object), `name` (string)
121
122	```bash
123	curl \
124	-X POST \
125	-H "Authorization: Bearer $TELNYX_API_KEY" \
126	-H "Content-Type: application/json" \
127	"https://api.telnyx.com/v2/ai/conversations"
128	```
129
130	Returns: `created_at` (date-time), `id` (uuid), `last_message_at` (date-time), `metadata` (object), `name` (string)
131
132	## Get Insight Template Groups
133
134	Get all insight groups
135
136	`GET /ai/conversations/insight-groups`
137
138	```bash
139	curl -H "Authorization: Bearer $TELNYX_API_KEY

People who liked this also viewed

6 picks

Type