team-telnyx Telnyx Ai Inference - JavaScript
Installation
npm install telnyx@6.74.2
Setup
import Telnyx from 'telnyx';
const client = new Telnyx({
apiKey: process.env['TELNYX_API_KEY'], // This is the default and can be omitted
});
All examples below assume client is already initialized as shown above.
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:
try {
const result = await client.messages.send({ to: '+13125550001', from: '+13125550002', text: 'Hello' });
} catch (err) {
if (err instanceof Telnyx.APIConnectionError) {
console.error('Network error — check connectivity and retry');
} else if (err instanceof Telnyx.RateLimitError) {
// 429: rate limited — wait and retry with exponential backoff
const retryAfter = err.headers?.['retry-after'] || 1;
await new Promise(r => setTimeout(r, retryAfter * 1000));
} else if (err instanceof Telnyx.APIError) {
console.error(`API error ${err.status}: ${err.message}`);
if (err.status === 422) {
console.error('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).
Important Notes
- Pagination: List methods return an auto-paginating iterator. Use
for await (const item of result) { ... }to iterate through all pages automatically.
Transcribe speech to text
Transcribe speech to text. This endpoint is consistent with the OpenAI Transcription API and may be used with the OpenAI JS or Python SDK.
POST /ai/audio/transcriptions
import fs from 'fs';
const response = await client.ai.audio.transcribe({ model: 'distil-whisper/distil-large-v2' });
console.log(response.text);
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 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)
const response = await client.ai.chat.createCompletion({
messages: [
{ role: 'system', content: 'You are a friendly chatbot.' },
{ role: 'user', content: 'Hello, world!' },
],
});
console.log(response);
List conversations
Retrieve a list of all AI conversations configured by the user. Supports PostgREST-style query parameters 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
const conversations = await client.ai.conversations.list();
console.log(conversations.data);
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)
const conversation = await client.ai.conversations.create();
console.log(conversation.id);
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
const response = await client.ai.conversations.conversationInsights.aggregate();
console.log(response.data);
Returns: record_count (integer)
Get Insight Template Groups
Get all insight groups
GET /ai/conversations/insight-groups
// Automatically fetches more pages as needed.
for await (const insightTemplateGroup of client.ai.conversations.insightGroups.retrieveInsightGroups()) {
console.log(insightTemplateGroup.id);
}
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)
const insightTemplateGroupDetail = await client.ai.conversations.insightGroups.insightGroups({
name: 'my-resource',
});
console.log(insightTemplateGroupDetail.data);
Returns: created_at (date-time), description (string), id (uuid), insights (array[object]), name (string), webhook (string)
Get Insight Template Group
Get insight group by ID
GET /ai/conversations/insight-groups/{group_id}
const insightTemplateGroupDetail = await client.ai.conversations.insightGroups.retrieve(
'182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);
console.log(insightTemplateGroupDetail.data);
Returns: created_at (date-time), description (string), id (uuid), insights (array[object]), name (string), webhook (string)
Update Insight Template Group
Update an insight template group
PUT /ai/conversations/insight-groups/{group_id}
Optional: description (string), name (string), webhook (string)
const insightTemplateGroupDetail = await client.ai.conversations.insightGroups.update(
'182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);
console.log(insightTemplateGroupDetail.data);
Returns: created_at (date-time), description (string), id (uuid), insights (array[object]), name (string), webhook (string)
Delete Insight Template Group
Delete insight group by ID
DELETE /ai/conversations/insight-groups/{group_id}
await client.ai.conversations.insightGroups.delete('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');
Assign Insight Template To Group
Assign an insight to a group
POST /ai/conversations/insight-groups/{group_id}/insights/{insight_id}/assign
await client.ai.conversations.insightGroups.insights.assign(
'182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
{ group_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' },
);
Unassign Insight Template From Group
Remove an insight from a group
DELETE /ai/conversations/insight-groups/{group_id}/insights/{insight_id}/unassign
await client.ai.conversations.insightGroups.insights.deleteUnassign(
'182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
{ group_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' },
);
Get Insight Templates
Get all insights
GET /ai/conversations/insights
// Automatically fetches more pages as needed.
for await (const insightTemplate of client.ai.conversations.insights.list()) {
console.log(insightTemplate.id);
}
Returns: created_at (date-time), id (uuid), insight_type (enum: custom, default), instructions (string), json_schema (object), name (string), webhook (string)
Create Insight Template
Create a new insight
POST /ai/conversations/insights — Required: instructions, name
Optional: json_schema (object), webhook (string)
const insightTemplateDetail = await client.ai.conversations.insights.create({
instructions: 'You are a helpful assistant.',
name: 'my-resource',
});
console.log(insightTemplateDetail.data);
Returns: created_at (date-time), id (uuid), insight_type (enum: custom, default), instructions (string), json_schema (object), name (string), webhook (string)
Get Insight Template
Get insight by ID
GET /ai/conversations/insights/{insight_id}
const insightTemplateDetail = await client.ai.conversations.insights.retrieve(
'182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);
console.log(insightTemplateDetail.data);
Returns: created_at (date-time), id (uuid), insight_type (enum: custom, default), instructions (string), json_schema (object), name (string), webhook (string)
Update Insight Template
Update an insight template
PUT /ai/conversations/insights/{insight_id}
Optional: instructions (string), json_schema (object), name (string), webhook (string)
const insightTemplateDetail = await client.ai.conversations.insights.update(
'182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);
console.log(insightTemplateDetail.data);
Returns: created_at (date-time), id (uuid), insight_type (enum: custom, default), instructions (string), json_schema (object), name (string), webhook (string)
Delete Insight Template
Delete insight by ID
DELETE /ai/conversations/insights/{insight_id}
await client.ai.conversations.insights.delete('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');
Get a conversation
Retrieve a specific AI conversation by its ID.
GET /ai/conversations/{conversation_id}
const conversation = await client.ai.conversations.retrieve('550e8400-e29b-41d4-a716-446655440000');
console.log(conversation.data);
Returns: created_at (date-time), id (uuid), last_message_at (date-time), metadata (object), name (string)
Update conversation metadata
Update metadata for a specific conversation.
PUT /ai/conversations/{conversation_id}
Optional: metadata (object)
const conversation = await client.ai.conversations.update('550e8400-e29b-41d4-a716-446655440000');
console.log(conversation.data);
Returns: created_at (date-time), id (uuid), last_message_at (date-time), metadata (object), name (string)
Delete a conversation
Delete a specific conversation by its ID.
DELETE /ai/conversations/{conversation_id}
await client.ai.conversations.delete('550e8400-e29b-41d4-a716-446655440000');
Get insights for a conversation
Retrieve insights for a specific conversation
GET /ai/conversations/{conversation_id}/conversations-insights
const response = await client.ai.conversations.retrieveConversationsInsights('550e8400-e29b-41d4-a716-446655440000');
console.log(response.data);
Returns: conversation_insights (array[object]), created_at (date-time), id (string), status (enum: pending, in_progress, completed, failed)
Create Message
Add a new message to the conversation. Used to insert a new messages to a conversation manually ( without using chat endpoint )
POST /ai/conversations/{conversation_id}/message — Required: role
Optional: content (string), metadata (object), name (string), sent_at (date-time), tool_call_id (string), tool_calls (array[object]), tool_choice (object)
await client.ai.conversations.addMessage('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e', { role: 'user' });
Get conversation messages
Retrieve messages for a specific conversation, including tool calls made by the assistant.
GET /ai/conversations/{conversation_id}/messages
// Automatically fetches more pages as needed.
for await (const messageListResponse of client.ai.conversations.messages.list('550e8400-e29b-41d4-a716-446655440000')) {
console.log(messageListResponse.role);
}
Returns: created_at (date-time), role (enum: user, assistant, tool), sent_at (date-time), text (string), tool_calls (array[object])
Get Tasks by Status
Retrieve tasks for the user that are either queued, processing, failed, success or partial_success based on the query string. Defaults to queued and processing.
GET /ai/embeddings
const embeddings = await client.ai.embeddings.list();
console.log(embeddings.data);
Returns: bucket (string), created_at (date-time), finished_at (date-time), status (enum: queued, processing, success, failure, partial_success), task_id (string), task_name (string), user_id (string)
Embed documents
Perform embedding on a Telnyx Storage Bucket using an embedding model. The current supported file types are:
- HTML
- txt/unstructured text files
- json
- csv
- audio / video (mp3, mp4, mpeg, mpga, m4a, wav, or webm ) - Max of 100mb file size. Any files not matching the above types will be attempted to be embedded as unstructured text.
POST /ai/embeddings — Required: bucket_name
Optional: document_chunk_overlap_size (integer), document_chunk_size (integer), embedding_model (object), loader (object)
const embeddingResponse = await client.ai.embeddings.create({ bucket_name: 'my-bucket' });
console.log(embeddingResponse.data);
Returns: created_at (string), finished_at (string | null), status (string), task_id (uuid), task_name (string), user_id (uuid)
List embedded buckets
Get all embedding buckets for a user.
GET /ai/embeddings/buckets
const buckets = await client.ai.embeddings.buckets.list();
console.log(buckets.data);
Returns: buckets (array[string])
Get file-level embedding statuses for a bucket
Get all embedded files for a given user bucket, including their processing status.
GET /ai/embeddings/buckets/{bucket_name}
const bucket = await client.ai.embeddings.buckets.retrieve('bucket_name');
console.log(bucket.data);
Returns: created_at (date-time), error_reason (string), filename (string), last_embedded_at (date-time), status (string), updated_at (date-time)
Disable AI for an Embedded Bucket
Deletes an entire bucket's embeddings and disables the bucket for AI-use, returning it to normal storage pricing.
DELETE /ai/embeddings/buckets/{bucket_name}
await client.ai.embeddings.buckets.delete('bucket_name');
Search for documents
Perform a similarity search on a Telnyx Storage Bucket, returning the most similar num_docs document chunks to the query. Currently the only available distance metric is cosine similarity which will return a distance between 0 and 1. The lower the distance, the more similar the returned document chunks are to the query.
POST /ai/embeddings/similarity-search — Required: bucket_name, query
Optional: num_of_docs (integer)
const response = await client.ai.embeddings.similaritySearch({
bucket_name: 'my-bucket',
query: 'What is Telnyx?',
});
console.log(response.data);
Returns: distance (number), document_chunk (string), metadata (object)
Embed URL content
Embed website content from a specified URL, including child pages up to 5 levels deep within the same domain. The process crawls and loads content from the main URL and its linked pages into a Telnyx Cloud Storage bucket.
POST /ai/embeddings/url — Required: url, bucket_name
const embeddingResponse = await client.ai.embeddings.url({
bucket_name: 'my-bucket',
url: 'https://example.com/resource',
});
console.log(embeddingResponse.data);
Returns: created_at (string), finished_at (string | null), status (string), task_id (uuid), task_name (string), user_id (uuid)
Get an embedding task's status
Check the status of a current embedding task. Will be one of the following:
queued- Task is waiting to be picked up by a workerprocessing- The embedding task is runningsuccess- Task completed successfully and the bucket is embeddedfailure- Task failed and no files were embedded successfullypartial_success- Some files were embedded successfully, but at least one failed
GET /ai/embeddings/{task_id}
const embedding = await client.ai.embeddings.retrieve('task_id');
console.log(embedding.data);
Returns: created_at (string), finished_at (string), status (enum: queued, processing, success, failure, partial_success), task_id (uuid), task_name (string)
List fine tuning jobs
Retrieve a list of all fine tuning jobs created by the user.
GET /ai/fine_tuning/jobs
const jobs = await client.ai.fineTuning.jobs.list();
console.log(jobs.data);
Returns: created_at (integer), finished_at (integer | null), hyperparameters (object), id (string), model (string), organization_id (string), status (enum: queued, running, succeeded, failed, cancelled), trained_tokens (integer | null), training_file (string)
Create a fine tuning job
Create a new fine tuning job.
POST /ai/fine_tuning/jobs — Required: model, training_file
Optional: hyperparameters (object), suffix (string)
const fineTuningJob = await client.ai.fineTuning.jobs.create({
model: 'openai/gpt-4o',
training_file: 'training-data.jsonl',
});
console.log(fineTuningJob.id);
Returns: created_at (integer), finished_at (integer | null), hyperparameters (object), id (string), model (string), organization_id (string), status (enum: queued, running, succeeded, failed, cancelled), trained_tokens (integer | null), training_file (string)
Get a fine tuning job
Retrieve a fine tuning job by job_id.
GET /ai/fine_tuning/jobs/{job_id}
const fineTuningJob = await client.ai.fineTuning.jobs.retrieve('job_id');
console.log(fineTuningJob.id);
Returns: created_at (integer), finished_at (integer | null), hyperparameters (object), id (string), model (string), organization_id (string), status (enum: queued, running, succeeded, failed, cancelled), trained_tokens (integer | null), training_file (string)
Cancel a fine tuning job
Cancel a fine tuning job.
POST /ai/fine_tuning/jobs/{job_id}/cancel
const fineTuningJob = await client.ai.fineTuning.jobs.cancel('job_id');
console.log(fineTuningJob.id);
Returns: created_at (integer), finished_at (integer | null), hyperparameters (object), id (string), model (string), organization_id (string), status (enum: queued, running, succeeded, failed, cancelled), trained_tokens (integer | null), training_file (string)
Get available models
Deprecated: Use GET /v2/ai/openai/models instead. Returns the same ModelsResponse payload as the OpenAI-compatible endpoint — open-source LLMs hosted on Telnyx (e.g. moonshotai/Kimi-K2.6, zai-org/GLM-5.1-FP8, MiniMaxAI/MiniMax-M2.7), embedding models, and fine-tuned models — kept around for backwards compatibility.
GET /ai/models
const response = await client.ai.retrieveModels();
console.log(response.data);
Returns: base_model (string | null), context_length (integer), created (date-time), description (string | null), id (string), is_fine_tunable (boolean), is_vision_supported (boolean), languages (array[string]), license (string), max_completion_tokens (integer | null), object (string), organization (string), owned_by (string), parameters (integer), parameters_str (string | null), pricing (object), recommended_for_assistants (boolean), regions (array[string]), task (string), tier (enum: small, medium, large, unlisted)
Create embeddings
Creates an embedding vector representing the input text. This endpoint is compatible with the OpenAI Embeddings API and may be used with the OpenAI JS or Python SDK by setting the base URL to https://api.telnyx.com/v2/ai/openai.
POST /ai/openai/embeddings — Required: input, model
Optional: dimensions (integer), encoding_format (enum: float, base64), user (string)
const response = await client.ai.openai.embeddings.createEmbeddings({
input: 'The quick brown fox jumps over the lazy dog',
model: 'thenlper/gte-large',
});
console.log(response.data);
Returns: data (array[object]), model (string), object (string), usage (object)
List embedding models
Returns a list of available embedding models. This endpoint is compatible with the OpenAI Models API format.
GET /ai/openai/embeddings/models
const response = await client.ai.openai.embeddings.listEmbeddingModels();
console.log(response.data);
Returns: created (integer), id (string), object (string), owned_by (string)
Create a response
Deprecated: Use POST /v2/ai/openai/responses instead. This endpoint is compatible with the OpenAI Responses API and may be used with the OpenAI JS or Python SDK. Response id parameter is not supported at the moment. Use the conversation parameter with a Telnyx Conversation ID to leverage persistent conversations.
POST /ai/responses
const response = await client.ai.createResponseDeprecated({ body: { model: 'bar', input: 'bar' } });
console.log(response);
Summarize file content
Generate a summary of a file's contents. Supports the following text formats:
- PDF, HTML, txt, json, csv
Supports the following media formats (billed for both the transcription and summary):
- flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm
- Up to 100 MB
POST /ai/summarize — Required: bucket, filename
Optional: system_prompt (string)
const response = await client.ai.summarize({ bucket: 'my-bucket', filename: 'data.csv' });
console.log(response.data);
Returns: summary (string)
Get all Speech to Text batch report requests
Retrieves all Speech to Text batch report requests for the authenticated user
GET /legacy/reporting/batch_detail_records/speech_to_text
const speechToTexts = await client.legacy.reporting.batchDetailRecords.speechToText.list();
console.log(speechToTexts.data);
Returns: created_at (date-time), download_link (string), end_date (date-time), id (string), record_type (string), start_date (date-time), status (enum: PENDING, COMPLETE, FAILED, EXPIRED)
Create a new Speech to Text batch report request
Creates a new Speech to Text batch report request with the specified filters
POST /legacy/reporting/batch_detail_records/speech_to_text — Required: start_date, end_date
const speechToText = await client.legacy.reporting.batchDetailRecords.speechToText.create({
end_date: '2020-07-01T00:00:00-06:00',
start_date: '2020-07-01T00:00:00-06:00',
});
console.log(speechToText.data);
Returns: created_at (date-time), download_link (string), end_date (date-time), id (string), record_type (string), start_date (date-time), status (enum: PENDING, COMPLETE, FAILED, EXPIRED)
Get a specific Speech to Text batch report request
Retrieves a specific Speech to Text batch report request by ID
GET /legacy/reporting/batch_detail_records/speech_to_text/{id}
const speechToText = await client.legacy.reporting.batchDetailRecords.speechToText.retrieve(
'182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);
console.log(speechToText.data);
Returns: created_at (date-time), download_link (string), end_date (date-time), id (string), record_type (string), start_date (date-time), status (enum: PENDING, COMPLETE, FAILED, EXPIRED)
Delete a Speech to Text batch report request
Deletes a specific Speech to Text batch report request by ID
DELETE /legacy/reporting/batch_detail_records/speech_to_text/{id}
const speechToText = await client.legacy.reporting.batchDetailRecords.speechToText.delete(
'182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);
console.log(speechToText.data);
Returns: created_at (date-time), download_link (string), end_date (date-time), id (string), record_type (string), start_date (date-time), status (enum: PENDING, COMPLETE, FAILED, EXPIRED)
Get speech to text usage report
Generate and fetch speech to text usage report synchronously. This endpoint will both generate and fetch the speech to text report over a specified time period.
GET /legacy/reporting/usage_reports/speech_to_text
const response = await client.legacy.reporting.usageReports.retrieveSpeechToText();
console.log(response.data);
Returns: data (object)
Generate speech from text
Generate synthesized speech audio from text input. Returns audio in the requested format (binary audio stream, base64-encoded JSON, or an audio URL for later retrieval). Authentication is provided via the standard Authorization: Bearer header.
POST /text-to-speech/speech
Optional: aws (object), azure (object), disable_cache (boolean), elevenlabs (object), language (string), minimax (object), output_type (enum: binary_output, base64_output), provider (enum: aws, telnyx, azure, elevenlabs, minimax, rime, resemble, xai), resemble (object), rime (object), telnyx (object), text (string), text_type (enum: text, ssml), voice (string), voice_settings (object), xai (object)
const response = await client.textToSpeech.generate();
console.log(response.base64_audio);
Returns: base64_audio (string)
List available voices
Retrieve a list of available voices from one or all TTS providers. When provider is specified, returns voices for that provider only. Otherwise, returns voices from all providers.
GET /text-to-speech/voices
const response = await client.textToSpeech.listVoices();
console.log(response.voices);
Returns: voices (array[object])