Sold by: Smallest AI
Lightning v3.1 is Smallest AI's high-fidelity text-to-speech engine for production voice applications - 15 languages with automatic language detection and in-session code-switching, behind one unified API. Built for real-time use with 100ms latency at 20 concurrent requests and a 0.3 real-time factor (3.3x faster than playback), it delivers broadcast-quality 44.1 kHz audio with natural prosody and intonation. In independent evals it leads on naturalness and MOS, at 94.6% word accuracy (5.38% WER). Includes instant voice cloning from 5-15 seconds of audio, HTTP/SSE/WebSocket streaming, adjustable speed, and custom pronunciation dictionaries. Ideal for conversational AI, IVR and telephony, customer service automation, narration, accessibility, gaming, and audiobook generation. Procure via AWS Marketplace with usage-based pricing and consolidated billing.
Overview
Lightning v3.1 is Smallest AI's latest high-fidelity, low-latency text-to-speech model, delivering natural, expressive, broadcast-quality speech at a native 44.1 kHz sample rate. Optimized for real-time conversational AI and live streaming, it combines ultra-low latency with built-in voice cloning and genuinely conversational prosody.
Performance and quality:
- Real-time speed: 100ms latency at 20 concurrent requests and a 0.3 real-time factor - 3.3x faster than playback.
- Premium audio: native 44.1 kHz output with a 5.06 WVMOS score and near-perfect pronunciation (4.70/5.0) and intonation (4.71/5.0) on the Seed TTS benchmark.
- Competitive intelligibility: 94.6% word accuracy (5.38% WER) and 1.54% character error rate in agent-call (streamed) evaluation.
- Benchmarked on naturalness and MOS using an LLM-as-a-Judge framework over 1,088 English samples across selected publicly available text-to-speech systems.
Capabilities:
- 15 languages - English, Spanish, Hindi, Tamil, Kannada, Telugu, Malayalam, Marathi, Gujarati, plus French, Italian, Dutch, Swedish, Portuguese, and German (beta) - with automatic language detection and intra-session code-switching, no restarts or reconnections.
- Instant voice cloning from just 5-15 seconds of audio, self-serve via API and console, with cross-lingual cloning and accent retention.
- Flexible streaming: synchronous HTTP, server-sent events (SSE), and WebSocket for real-time applications.
- Adjustable playback speed (0.5x-2.0x) and custom pronunciation dictionaries for brand names, acronyms, and domain-specific terms.
- Output in PCM, MP3, WAV, and mulaw at 8 / 16 / 24 / 44.1 kHz sample rates.
Built for scale and easy integration with a clean, enterprise-grade API. Common use cases include voice assistants and conversational agents, interactive chatbots, IVR and telephony, customer-service automation, real-time narration and live streaming, accessibility tools, dynamic gaming voices, and podcast/audiobook generation. Procure Lightning v3.1 through AWS Marketplace to accelerate onboarding with usage-based pricing and consolidated billing on your existing AWS invoice - ideal for trials, POCs, and scaling to production while drawing down AWS commitments. Lightning runs on AWS infrastructure for lowest latency, and supports private offers and enterprise MSAs for committed-use deals. For compliance documentation (GDPR, SOC 2, HIPAA), contact support@smallest.ai .
Highlights
- Real-time TTS for natural conversations: 100ms latency at 20 concurrent requests and 0.3 real-time factor (3.3x faster than playback), with broadcast-quality 44.1 kHz audio and 94.6% word accuracy.
- Truly multilingual: 15 languages with automatic language detection and in-session code-switching - leading benchmarks on naturalness and MOS.
- Instant voice cloning from 5-15 seconds of audio, plus HTTP/SSE/WebSocket streaming, adjustable speed, and custom pronunciation dictionaries - billed through AWS Marketplace with consolidated billing.
Details
Sold by
Categories
Delivery method
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on the duration and terms of your contract with the vendor, and additional usage. You pay upfront or in installments according to your contract terms with the vendor. This entitles you to a specified quantity of use for the contract duration. Usage-based pricing is in effect for overages or additional usage not covered in the contract. These charges are applied on top of the contract price. If you choose not to renew or replace your contract before the contract end date, access to your entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/month |
|---|---|---|
Business Plan | Business Plan which includes up to 115730 minutes of audio generated. | $1,999.00 |
Enterprise Plan | Contact gtm@smallest.ai for enterprise plans with customized pricing, concurrency, support, and more. Please do not checkout with this option. | $100,000.00 |
Dimension | Description | Cost/unit |
|---|---|---|
Overage | Per 1K Character | $0.025 |
Vendor refund policy
Please contact gtm@smallest.ai for refund information.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Resources
Vendor resources
Support
Vendor support
For technical support, contact support@smallest.ai For sales inquiries, reach GTM team (gtm@smallest.ai ; Harsh: +91-9819899421)
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.
Similar products
From the creators of PyTorch Lightning, the most advanced AI platform purpose-built for the Gen AI era. Use pre-built studios to jumpstart any use case. Code, prototype, train, and deploy AI apps, all in one place using the Lightning Studio.
IPFire is a Linux-based Open Source Firewall
PyTorch Lightning + MLflow - MLOps Ready provides a complete machine learning operations environment pre-configured for AWS instances. This solution includes PyTorch Lightning for organized deep learning workflows and MLflow for comprehensive experiment tracking and model management.
IPFire is a Linux-based Open Source Firewall
Easily create APIs from existing enterprise data. Connect CData API Server to any RDBMS, NoSQL database, or custom app, and API Server instantly generates flexible, comprehensive, and fully documented APIs.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.