One REST endpoint, dozens of voices, sub-second latency. Ship lifelike speech, cloning, and dubbing in any language without managing a single GPU.
The Raritone API provides developers with a comprehensive set of endpoints to integrate AI-powered speech capabilities into web applications, mobile apps, enterprise software, and customer experiences. Designed for performance and scalability, the API enables seamless voice generation and speech processing with minimal integration effort.
A single, coherent surface for every voice workflow — from generation and cloning to streaming and management. Build once, ship everywhere.
Generate natural, human-like speech from text using a wide selection of AI voices.
/v1/aiConvert text into high-quality audio with support for multiple voices, languages, and speech styles.
/v1/text-to-speechConvert spoken audio into accurate text for transcription, analytics, and automation.
/v1/speech-to-textCreate and manage authorized custom voice profiles for personalized voice experiences.
/v1/voiceManage voice profiles, generated audio, and voice settings from a single API.
/v1/voiceEnable real-time speech generation and audio streaming for live applications.
/v1/streamingA complete developer surface built for production — from auth and streaming to webhooks, analytics, and SDKs in every language you care about.
Predictable resource-oriented URLs, standard HTTP verbs, and clear status codes.
Clean, typed payloads you can pipe straight into your app.
Chunked audio over the wire — first byte in under 300ms.
Pin to a version, upgrade on your schedule.
A clear path for engineers — sign up, ship voice in your product the same afternoon.
Sign up in minutes and access the developer dashboard.
Create a secure, scoped key directly from your dashboard.
Explore endpoints, parameters, and runnable code samples.
Fire a curl or SDK call and stream audio back in under a second.
Ship to production with rate-limit-aware SDKs and webhooks.
A clean, predictable surface for every voice workflow. Browse the core resources below and start integrating in minutes.
/v1/voice/generateGenerate AI speech from text using selected voices.
/v1/stt/transcribeUpload audio files and receive accurate transcriptions.
/v1/voices/cloneCreate and manage authorized custom voice profiles.
/v1/account/usageMonitor API usage, quotas, billing, and application settings.
Raritone is designed with enterprise-grade security and dependable infrastructure.
Compliance
SOC 2 / GDPR / HIPAA ready
console
Security checks
Certified
SOC 2
256-bit AES
Docs, SDKs, reference, and support — curated for the way you ship. Pick a thread and pull.
Eight reasons engineers pick Raritone for voice — from sub-200ms streaming to globally available infrastructure that scales without a ticket.
Plug-in REST endpoints with SDKs for every stack.
Clear references, runnable code, every parameter explained.
Sub-200ms p95 streaming response times.
Multi-region deployments, edge POPs everywhere.
SOC 2 aligned controls, encryption everywhere.
Burst to millions of requests with auto-scaling.
99.99% uptime SLA across regions.
REST, streaming, webhooks, SDKs — pick your fit.
Everything you need to know about authentication, quotas, commercial usage, and shipping with the Raritone API.


“Shipped voice into our app in an afternoon. The SDK ergonomics are honestly better than the docs let on.”
— Staff Eng · YC W24
Create a Raritone account, sign in to the developer dashboard, and generate an API key from your account settings.
The API is language-agnostic and can be integrated with any language capable of making HTTPS requests. Client libraries and examples are available for popular programming languages.
Yes. All API requests require authentication using a valid API key.
Usage limits vary depending on your subscription plan. Current quotas and usage details are available in your dashboard.
Yes. Commercial use is available according to the terms of your selected subscription plan.
Still curious about something?
Our developer engineers reply in under four hours.

Integrate AI voice generation, speech recognition, text-to-speech, and voice cloning into your applications with a secure, scalable, and developer-friendly API.