Tools

Generate Speech

Convert text to spoken audio using Groq's text-to-speech API. Supports English and Arabic voices with configurable voice selection, speed, and output format. Some models support vocal direction tags like `[cheerful]` embedded in the input text.

List Batches

List all batch processing jobs in your GroqCloud organization. Returns batch IDs, statuses, and progress information for all current and past batches.

Cancel Batch

Cancel an in-progress batch processing job on GroqCloud. The batch status will transition to "cancelling" and then "cancelled".

Moderate Content

Evaluate text content for safety and policy compliance using Groq's moderation models. Supports custom safety policies with GPT-OSS-Safeguard and prompt injection detection with Llama Prompt Guard models.

List Models

Retrieve the list of all available models on GroqCloud. Returns model IDs, context window sizes, ownership, and status information. Useful for discovering which models are available for text generation, vision, audio, and other tasks.

Transcribe Audio

Transcribe audio to text using Groq's Whisper models with near-instant speed. Supports multiple audio formats and languages. Provide an audio file URL and receive the transcribed text.

Analyze Image

Analyze images using Groq's multimodal vision models. Provide an image (via URL or base64 data) along with a text prompt to get descriptions, answers to questions, or structured analysis of visual content.

Generate Text

Generate text using Groq's chat completions API with ultra-low latency inference. Supports conversational interactions, content generation, structured outputs, tool/function calling, and reasoning models. Pass a series of messages and receive a model-generated response.

Create Batch

Create a batch processing job on GroqCloud. Use an uploaded batch JSONL file or provide JSONL content to upload and create the batch in one step. Each line should contain a request object with custom_id, method, url, and body fields for the chat completions endpoint.

Get Model

Retrieve detailed information about a specific model on GroqCloud, including context window size, max completion tokens, and availability status.

Translate Audio

Translate spoken audio into English text using Groq's Whisper models. Accepts audio in any supported language and produces an English translation. Provide an audio file URL and receive the translated text.

Get Batch

Retrieve the status and details of a batch processing job on GroqCloud. Returns current status, progress counts, and output file information.

Create Response

Generate a model response using Groq's Responses API. Supports simple text input, message arrays, structured outputs, tool definitions, and reasoning controls through the OpenAI-compatible /responses endpoint.

Download File

Download the content of a Groq Cloud file, such as a batch output JSONL file. File content is returned as a Slate text attachment.

Upload File

Upload a JSONL file to Groq Cloud for Batch API processing. Uploaded files use purpose "batch" and can be passed to Create Batch by file ID.

Delete File

Delete a Groq Cloud file by ID.

Get File

Retrieve metadata for a Groq Cloud file by ID.

List Files

List files uploaded to Groq Cloud, including batch input and batch output files.