Introduction

A quick overview of Rime’s speech platform: the default model, deployment options, enterprise features, pricing, and the developer surfaces you build on.

Rime is voice AI made for human conversation: natural, low-latency speech for production voice agents, IVR, and telephony.

Its flagship model, Coda, is trained on full-duplex conversations between real people, not voice actors or audiobook narrators. Coda has top-rated voice quality in human evaluations and runs at sub-100ms model latency. The cloud API offers 184 Coda voices across 8 languages. Coda can also run in your VPC or fully on-premises, where the packaged language set may differ.

Start here

Pick the one that matches what you are doing. Each is a complete path, not an overview.

Generate your first audio

One HTTP request, a playable file back, in about five minutes. Start here if you are evaluating Rime or adding speech to an existing backend.

Build a real-time voice agent

A conversational agent that listens and speaks. Complete LiveKit tutorial, or direct WebSocket starters for Next.js, Vite, Express, Node, and FastAPI.

Try Rime from the terminal

Generate and play speech without writing any code. The fastest way to hear a voice and check response speed.

Run Rime on your own infrastructure

Deploy supported models in your VPC or fully on-premises, so audio and text stay inside your network.

Migrate off Arcana

Cloud Arcana requests switch to Coda on August 15, 2026. The request shape does not change, but Coda’s voice lineup was selected rather than ported, so check whether your voice is on it.

Diagnose a failing request

What each status code and WebSocket close code means, what the client observes per transport, and what to capture for support.

Rime at a glance

Rime is a text-to-speech platform for real-time voice: conversational agents, IVR, telephony, and any product that needs to speak.

Area	Summary
Product	Low-latency neural text-to-speech. The flagship model, Coda, reaches sub-100ms model latency (sub-200ms end to end over the cloud API).
Reach	500+ voices across the model lineup (184 on Coda) in 9 languages, plus instant custom voice cloning.
Deployment	Regional cloud API, virtual private cloud (VPC), or on-premises with Docker Compose or Kubernetes.
Enterprise	Unlimited concurrency, unlimited custom voice clones, SLAs, and dedicated support.
Security and compliance	SOC 2 reports and a HIPAA Business Associate Agreement (BAA). VPC and on-prem keep audio and text inside your own network.
Pricing	Usage-based. Starter is $0.05 per 1,000 characters with 3,000 free minutes and 20 concurrent streams. Enterprise uses custom volume pricing. See rime.ai/pricing.

Talk to the team about enterprise, on-prem, or volume pricing

Custom deployments, compliance (SOC 2, HIPAA), SLAs, and dedicated support for production scale.

Start with Coda

Coda is the default model for new projects and the recommended destination for cloud Arcana traffic. Existing cloud integrations can switch by setting modelId: coda; the rest of the API contract stays the same. Cloud Arcana requests switch to Coda on August 15, 2026. See Migrate from Arcana to Coda for the cutover procedure and what changes.

Coda pairs an LLM backbone with a dedicated speech inference engine trained on full-duplex conversations between real people. Through the cloud API, it serves eight languages: English, Arabic, French, German, Hindi, Japanese, Portuguese, and Spanish. Each voice serves one of them, so the language you need determines which voices are available to you.

Speech capabilities

Generate speech

Turn text into playable or downloadable audio in formats suited to web, mobile, telephony, and media workflows.

Stream speech in real time

Use HTTP for simple streaming responses or persistent WebSockets for the tightest conversational loop, with timestamps and interruption handling.

Choose voices, models, and languages

Browse every voice on Coda and Mist v3, grouped by language, with the gender, age, and country the catalog publishes for each.

Shape how speech sounds

Guide delivery, pacing, spelling, pauses, pronunciation, and the way numbers, dates, and other text are spoken.

Build voice agents

Begin with a complete LiveKit tutorial or connect Rime directly from Next.js, Vite, Express, Node.js, or FastAPI.

Connect voice platforms

Integrate with LiveKit, Pipecat, Vapi, Daily, SignalWire, VideoSDK, and other voice application frameworks.

Create a custom voice

Make a branded enterprise voice available to the same speech API as Rime’s voice catalog.

Run Rime in your environment

Use Rime’s regional cloud endpoints or deploy supported models on your own infrastructure.

Developer surfaces

Dashboard

Explore, preview, and save voices; generate speech and inspect normalized text. Create API tokens, follow setup progress, manage teams, and review usage and billing.

HTTP and WebSocket APIs

Generate complete audio responses, stream audio, receive word timestamps, list voices, and use Rime’s language tools.

Application code

Use standard HTTP and WebSocket clients from Python, JavaScript, Go, or any server-side language; no Rime-specific SDK is required. The cheat sheet is the compact parameter and endpoint reference.

CLI

Generate, play, and save speech, inspect usage, and test response speed from the terminal.

MCP server

Let Claude, Codex, and compatible tools browse voices, generate samples, inspect pronunciation and text normalization, and scaffold integrations.

Application integrations

Use Rime with supported voice-agent frameworks, telephony services, deployment platforms, and application builders.

One Rime API token authenticates the API, CLI, MCP tools, and supported integrations. Manage tokens, team access, and billing in the Rime dashboard.