Overview

Product video
Deepgram is the leading voice AI platform for enterprise use cases, offering both foundational models, pre-trained on extensive datasets and custom models, that can be tailored with client-specific data to meet unique requirements. Over 200,000 developers build on Deepgram's infrastructure to create voice-enabled AI applications such as real-time transcription, meeting assistants, and voice AI chatbots and virtual agents.
Deepgram offers a suite of Voice AI products:
Speech-to-Text API: Real-time transcription with high accuracy. Text-to-Speech API: Natural, human-like speech generation from text. Voice Agent API: Real-time AI voice agents for dynamic interactions. Audio Intelligence: Extracts insights from audio with task-specific models for sentiment, intent, and topic detection.
Deepgram's enterprise-ready platform provides scalable, cost-efficient voice AI infrastructure for mission-critical applications. Its high-performance, low-latency runtime supports features like adaptable model fine-tuning, automated transcription, and synthetic data generation, optimizing enterprise workflows. Deepgram also adheres to PCI, SOC 2, and HIPAA standards, ensuring secure, seamless integration with existing cloud platforms and systems.
Explore our API Playground or sign up to start building with $200 in free credits.
Highlights
- Unmatched ASR accuracy in noisy conditions: The Nova-3 speech-to-text model achieves a 54.2% lower word error rate than competitors, supports real-time multilingual context switching, and allows self-service customization to boost up to 100 key terms.
- Natural, expressive speech generation: The Aura text-to-speech model delivers ultra-low latency (sub-200ms) and human-like voice synthesis, while being cost-efficient and optimized for high-throughput applications.
- Enterprise runtime platform: Deepgrams high-performance runtime and developer platform includes capabilities such as synthetic data generation, model curation, and model hot-swapping, enabling developers to build, customize, and optimize voice-enabled applications effectively.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Description | Cost/unit |
|---|---|---|
Agentic Commerce x402 | Agentic Commerce meters this unit to bill buyers the seller's x402 quote price. | $1.00 |
Vendor refund policy
n/a
Custom pricing options
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
API-Based Agents & Tools
API-Based Agents and Tools integrate through standard web protocols. Your applications can make API calls to access agent capabilities and receive responses.
Additional details
Usage instructions
API
How to pay for this API
This API is sold pay-per-request through AWS Marketplace using x402. Charges are billed in USD to your AWS account under AWS Marketplace. To call it, set up Amazon Bedrock AgentCore payments in your AWS account (a Payment Manager and a payment session with a spend limit), which your agent uses to obtain the AWS Marketplace payment token.
Send your request to the endpoint below. The API returns HTTP 402 Payment Required with an AWS Marketplace x402 price quote (extra.quoteToken) in the PAYMENT-REQUIRED header. Pass that 402 response to AgentCore payments (ProcessPayment, or the AgentCore payments plugin for Strands/LangGraph), then retry the same request with the payment token in the PAYMENT-SIGNATURE header. A successful call returns 200 with your result, and the PAYMENT-RESPONSE header contains your AWS Marketplace payment ID.
How to call this API
Three batch endpoints, all POST and priced per request. Call without payment first, pay the quote from the 402, then retry the same request.
Speech-to-text: POST <https://x402.deepgram.com/v1/listen>
- Price: $0.004333 per audio minute (nova-3); $0.005167/min with language=multi. Add-ons per minute: keyterm $0.001333, redact $0.002, detect_entities $0.001667.
- Query parameters: Deepgram /v1/listen parameters, e.g. model=nova-3, language, smart_format=true, diarize=true. callback is not supported; results are returned synchronously.
- Body, hosted audio (recommended, any length): Content-Type: application/json, {"url": "https://..."}. The URL must be fetchable by the API, e.g. an S3 presigned URL.
- Body, raw audio up to ~4.5 MB: Content-Type: audio/wav (or audio/mpeg, audio/flac, audio/ogg), body = audio bytes.
- Response: Deepgram transcript JSON.
Text-to-speech, Flux TTS (recommended): POST <https://x402.deepgram.com/v2/speak>
- Price: $0.045 per 1,000 input characters.
- Query parameters: model (required; a Flux TTS voice flux-{voice}-{language}, e.g. flux-haley-en), optional encoding (mp3 default, opus, flac, aac, linear16, mulaw, alaw), sample_rate, container, bit_rate, speed.
- Body: Content-Type: application/json, {"text": "..."}.
- Response: audio bytes (MP3 by default).
Text-to-speech, Aura-2: POST <https://x402.deepgram.com/v1/speak>
- Price: $0.03 per 1,000 input characters (aura-2 voices).
- Query parameters: model (an aura-2 voice, e.g. aura-2-thalia-en), optional encoding, sample_rate, container.
- Body: Content-Type: application/json, {"text": "..."}.
- Response: audio bytes (MP3 by default).
Notes
- A paid quote is valid for 5 minutes. A failed request (e.g. a 400 for an unsupported parameter) doesn't use up the payment; retry with corrected parameters as long as the new request costs no more than what you paid.
- Supported models: nova-3 (speech-to-text), Flux TTS voices on /v2/speak, and aura-2 voices on /v1/speak.
Resources
Vendor resources
Support
Vendor support
Email aws@deepgram.com
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.