# Rime Docs

## Docs

- [Streaming HTTP](https://docs.rime.ai/api-reference/arcana/http.md): Arcana streaming HTTP endpoint: synthesize speech and stream audio back in MP3, WAV, PCM, μ-law, or Opus.
- [Websockets](https://docs.rime.ai/api-reference/arcana/websockets.md): Arcana plain-text WebSocket (/ws): send text, receive raw audio bytes in the requested format.
- [Websockets JSON](https://docs.rime.ai/api-reference/arcana/websockets-json.md): Arcana JSON WebSocket (/ws3): structured events with base64 audio chunks and word-level timestamps.
- [Streaming HTTP](https://docs.rime.ai/api-reference/coda/http.md): Coda streaming HTTP endpoint: synthesize speech with Rime's flagship model and stream audio back.
- [Websockets](https://docs.rime.ai/api-reference/coda/websockets.md): Coda plain-text WebSocket (/ws): send text, receive raw audio bytes.
- [Websockets JSON](https://docs.rime.ai/api-reference/coda/websockets-json.md): Coda JSON WebSocket (/ws3): structured events with base64 audio chunks and word-level timestamps.
- [List Voice Details](https://docs.rime.ai/api-reference/data/voice-details.md): Voice metadata endpoint: list every Rime voice with demographic and model details.
- [List All Voices](https://docs.rime.ai/api-reference/data/voices-v2.md): List every Rime voice, keyed by modelId and language.
- [Streaming HTTP](https://docs.rime.ai/api-reference/mistv2/http.md): Mist v2 streaming HTTP endpoint.
- [MP3 over JSON](https://docs.rime.ai/api-reference/mistv2/json-mp3.md): Mist v2 non-streaming endpoint that returns base64 MP3 audio inside a JSON envelope.
- [μ-law over JSON](https://docs.rime.ai/api-reference/mistv2/json-mulaw.md): Mist v2 non-streaming endpoint that returns base64 G.711 μ-law audio inside a JSON envelope.
- [OGG over JSON](https://docs.rime.ai/api-reference/mistv2/json-ogg.md): Mist v2 non-streaming endpoint that returns base64 Opus/Ogg audio inside a JSON envelope.
- [WAV over JSON](https://docs.rime.ai/api-reference/mistv2/json-wav.md): Mist v2 non-streaming endpoint that returns base64 WAV audio inside a JSON envelope.
- [Server-sent Events](https://docs.rime.ai/api-reference/mistv2/sse.md): Mist v2 Server-Sent Events endpoint for streaming audio chunks over text/event-stream.
- [Websockets](https://docs.rime.ai/api-reference/mistv2/websockets.md): Mist v2 plain-text WebSocket (/ws): send text, receive raw audio bytes.
- [Websockets JSON](https://docs.rime.ai/api-reference/mistv2/websockets-json.md): Mist v2 JSON WebSocket (/ws2): structured events with base64 audio chunks and word-level timestamps.
- [Streaming HTTP](https://docs.rime.ai/api-reference/mistv3/http.md): Mist v3 streaming HTTP endpoint: low-latency TTS with the updated Mist engine.
- [Websockets](https://docs.rime.ai/api-reference/mistv3/websockets.md): Mist v3 plain-text WebSocket (/ws): send text, receive raw audio bytes.
- [Websockets JSON](https://docs.rime.ai/api-reference/mistv3/websockets-json.md): Mist v3 JSON WebSocket (/ws3): structured events with base64 audio chunks and word-level timestamps.
- [Coverage](https://docs.rime.ai/api-reference/other/oov.md): Coverage endpoint: check which input words are not yet in Rime's pronunciation dictionary.
- [Phonemize](https://docs.rime.ai/api-reference/other/phonemize.md): Phonemize endpoint: convert a recording of a word into a phonetic string in the Rime phonetic alphabet.
- [Text Normalization](https://docs.rime.ai/api-reference/other/textnorm.md): Text normalization endpoint: returns the normalized form of input text — exactly what the TTS model sees before synthesis.
- [Overview](https://docs.rime.ai/cli-reference/overview.md): Install and get started with the Rime CLI — a command-line tool for synthesizing and listening to AI speech.
- [Reference](https://docs.rime.ai/cli-reference/reference.md): Global flags, environment variables, configuration file format, audio formats, and metadata embedding for the Rime CLI.
- [Authentication](https://docs.rime.ai/cli-reference/rime-auth.md): Authenticate the Rime CLI using rime login, rime logout, and rime key.
- [rime config](https://docs.rime.ai/cli-reference/rime-config.md): Manage Rime CLI configuration and named environments with rime config subcommands.
- [rime curl](https://docs.rime.ai/cli-reference/rime-curl.md): Generate a ready-to-run curl command for the Rime TTS API.
- [rime hello & rime play](https://docs.rime.ai/cli-reference/rime-hello-play.md): Quick audio demo and terminal waveform playback with the Rime CLI.
- [Monitoring & Usage](https://docs.rime.ai/cli-reference/rime-monitoring.md): Measure latency, view character usage, and uninstall the Rime CLI.
- [rime tts](https://docs.rime.ai/cli-reference/rime-tts.md): Synthesize text to speech from the command line using the Rime CLI.
- [Troubleshooting](https://docs.rime.ai/cli-reference/troubleshooting.md): Fix common issues with the Rime CLI.
- [Abbreviations, acronyms, and initialisms](https://docs.rime.ai/docs/abbreviations.md): How Rime automatically pronounces common abbreviations, acronyms, and initialisms — and how to control pronunciation when needed.
- [Addresses, URLs, and emails](https://docs.rime.ai/docs/addresses.md): How Rime automatically expands street addresses, URLs, and email addresses into spoken form.
- [API authentication](https://docs.rime.ai/docs/api-authentication.md): How to authenticate with the Rime TTS API using a bearer token.
- [Baseten](https://docs.rime.ai/docs/baseten.md): Deploy Rime TTS on Baseten's serverless GPU infrastructure.
- [Cerebrium](https://docs.rime.ai/docs/cerebrium.md): Deploy Rime TTS on Cerebrium's serverless infrastructure.
- [Changelog](https://docs.rime.ai/docs/changelog.md): Release notes for Rime's TTS API and on-prem images.
- [Custom pauses](https://docs.rime.ai/docs/custom-pauses.md): Insert pauses of specific durations into Mist family synthesis using angle-bracket markers.
- [Custom pronunciation](https://docs.rime.ai/docs/custom-pronunciation.md): Specify pronunciations for uncommon words in Mist family synthesis using Rime's phonetic alphabet.
- [Daily](https://docs.rime.ai/docs/daily.md): Use Rime TTS with Daily's real-time video and voice platform via Pipecat.
- [Dates and times](https://docs.rime.ai/docs/dates.md): How Rime automatically expands dates and clock times into spoken form, and which formats are supported.
- [Homographs (Mist v2 only)](https://docs.rime.ai/docs/homographs.md): Disambiguate same-spelling-different-pronunciation words on Mist v2.
- [Introduction](https://docs.rime.ai/docs/introduction.md): Rime's text-to-speech API for real-time voice agents and IVR: low-latency streaming TTS with Coda, Arcana, and Mist models across English, Spanish, French, Portuguese, German, and Japanese.
- [Low-latency TTS for real-time voice agents](https://docs.rime.ai/docs/latency.md): Rime TTS latency benchmarks: sub-200ms end-to-end via the cloud API, sub-100ms on-prem with Coda, 37ms TTFA with Mist v3 — plus what affects response time and how to reduce it.
- [Linguistics and TTS](https://docs.rime.ai/docs/linguistics.md): Why TTS is hard: the one-to-many problem in linguistics and how Rime gives you customization controls.
- [LiveKit](https://docs.rime.ai/docs/livekit.md): Use Rime TTS with LiveKit Agents for real-time voice agents — plugin setup and streaming configuration.
- [Lovable](https://docs.rime.ai/docs/lovable.md): Build voice apps in Lovable using Rime's TTS.
- [MCP Quickstart](https://docs.rime.ai/docs/mcp.md): Connect Claude, Codex, or your IDE to Rime's hosted MCP server and hear your first voice.
- [Models](https://docs.rime.ai/docs/models.md): Pick the right Rime model: Coda (flagship), Arcana, Mist v3, Mist v2.
- [Numbers, currency, and measurements](https://docs.rime.ai/docs/numbers.md): How Rime automatically expands numbers, currency, ranges, measurements, phone numbers, and Roman numerals into spoken form.
- [Load balancing](https://docs.rime.ai/docs/on-prem/load-balancing.md): Load-balance Rime on-prem deployments using the ORCA cost-header signal.
- [Metrics](https://docs.rime.ai/docs/on-prem/metrics.md): Observability metrics exposed by Rime on-prem containers.
- [Performance tuning](https://docs.rime.ai/docs/on-prem/performance.md): Tune Rime on-prem deployments for throughput, latency, and concurrency.
- [Prometheus integration](https://docs.rime.ai/docs/on-prem/prometheus.md): Scrape Rime on-prem metrics with Prometheus.
- [Quickstart](https://docs.rime.ai/docs/on-prem/quickstart.md): Get Rime running on-prem in your environment.
- [OpenClaw document reader with Rime TTS Telegram bot](https://docs.rime.ai/docs/openclaw.md): Configure OpenClaw to be your personal reading assistant
- [Pipecat](https://docs.rime.ai/docs/pipecat.md): Build a real-time voice agent with Pipecat and Rime TTS — a full Python walkthrough from install to a working browser-based agent.
- [Pre-normalizing text](https://docs.rime.ai/docs/pre-normalization.md): Optional patterns you can pre-expand in your application before sending text to Rime. Use sparingly — Rime's normalizer handles most common formats natively without any preprocessing.
- [Privacy and compliance](https://docs.rime.ai/docs/privacy-compliance.md): Rime's security framework, SOC 2 Type II and HIPAA compliance, and how customer data is handled.
- [Prompting guide](https://docs.rime.ai/docs/prompting.md): How to prompt your LLM to produce text that sounds natural and normalizes cleanly through Rime.
- [CLI Quickstart](https://docs.rime.ai/docs/quickstart-cli.md): Install the Rime CLI and synthesize your first audio clip from the terminal.
- [TTS in five minutes](https://docs.rime.ai/docs/quickstart-five-minute.md): Generate your first Rime TTS audio clip in five minutes using cURL, Python, JavaScript, or TypeScript.
- [LiveKit Quickstart](https://docs.rime.ai/docs/quickstart-livekit.md): Build a real-time voice agent in your browser using LiveKit Agents + Rime TTS.
- [Regional endpoints](https://docs.rime.ai/docs/regional-endpoints.md): Route requests to the Rime region closest to your application for the lowest latency.
- [Replit](https://docs.rime.ai/docs/replit.md): Use Rime TTS inside Replit projects.
- [SignalWire](https://docs.rime.ai/docs/signalwire.md): Integrate Rime TTS with SignalWire's communications platform.
- [Playback speed](https://docs.rime.ai/docs/speed.md): Control speaking speed in Rime synthesis using speedAlpha and inlineSpeedAlpha.
- [Spell function](https://docs.rime.ai/docs/spell.md): Force letter-by-letter pronunciation of codes, IDs, and acronyms using the spell() function.
- [Streaming TTS](https://docs.rime.ai/docs/streaming.md): Stream Rime text-to-speech audio in real time over HTTP, WebSockets, or SSE — how to choose a transport, with runnable examples for low-latency voice agents.
- [Symbols and percentages](https://docs.rime.ai/docs/symbols.md): How Rime pronounces standalone symbols and how percentage values are expanded.
- [Text normalization](https://docs.rime.ai/docs/text-normalization.md): Rime automatically normalizes English text — numbers, dates, currency, phone numbers, measurements, and more — before synthesis.
- [Together AI](https://docs.rime.ai/docs/together-ai.md): Use Rime TTS via Together AI's inference platform.
- [Vapi](https://docs.rime.ai/docs/vapi.md): Connect Rime TTS to Vapi for phone-based voice agents and IVR systems.
- [VideoSDK](https://docs.rime.ai/docs/videosdk.md): Use Rime TTS with VideoSDK.
- [Voices](https://docs.rime.ai/docs/voices.md): Rime's TTS voice catalog across Coda, Arcana, and Mist — voices in English, Spanish, French, Portuguese, German, and Japanese, and how to pick a starter voice.
- [WebSocket API Overview](https://docs.rime.ai/docs/websockets.md): Stream Rime TTS in real time over WebSockets for voice agents: choose between /ws3 (flagship JSON), /ws2 (legacy JSON), and /ws (raw binary), with word-level timestamps and interruption handling.
- [Segmentation & Behavior Settings](https://docs.rime.ai/docs/websockets-segment.md): Control when synthesis fires over the WebSocket API using segment=never, bySentence, and immediate.
- [Playing audio](https://docs.rime.ai/mcp-reference/audio.md): How audio from synthesize_speech reaches your speakers — inline player, play URL, or MCP audio block.
- [Authentication](https://docs.rime.ai/mcp-reference/authentication.md): How Rime's MCP server resolves API keys — accepted headers, per-request handling, and which tools work without a key.
- [check_dictionary](https://docs.rime.ai/mcp-reference/check-dictionary.md): Check which words are not in Rime's pronunciation dictionary via the MCP server.
- [Connecting](https://docs.rime.ai/mcp-reference/connect.md): Connect Claude Code, Claude.ai, Claude Desktop, OpenAI Codex, or any MCP-compatible client to Rime's hosted MCP server.
- [generate_integration](https://docs.rime.ai/mcp-reference/generate-integration.md): Generate ready-to-run Pipecat or LiveKit voice-agent code wired to Rime TTS via the MCP server.
- [get_voice_details](https://docs.rime.ai/mcp-reference/get-voice-details.md): Get detailed Rime voice metadata — gender, age, accent, country, genre, model, and language — via the MCP server.
- [list_voices](https://docs.rime.ai/mcp-reference/list-voices.md): List Rime's voice catalog by model and language via the MCP server.
- [normalize_text](https://docs.rime.ai/mcp-reference/normalize-text.md): Preview how Rime normalizes text before synthesis via the MCP server.
- [Overview](https://docs.rime.ai/mcp-reference/overview.md): Rime's hosted MCP server — connect AI assistants to the voice catalog, linguistics tools, speech synthesis, and integration scaffolding.
- [Starter prompts](https://docs.rime.ai/mcp-reference/prompts.md): Optional MCP prompts that drive Rime's tools — find a voice, check a script, or scaffold a voice agent.
- [synthesize_speech](https://docs.rime.ai/mcp-reference/synthesize-speech.md): Generate an MP3 speech sample with Rime TTS via the MCP server, rendered in an inline audio player.
- [Pronunciation control](https://docs.rime.ai/platform/pronunciation-control.md): Check dictionary coverage, specify custom pronunciations, and request dictionary additions to control exactly how Rime speaks your words.
- [Rime phonetic alphabet](https://docs.rime.ai/platform/rime-phonetic-alphabet.md): Reference for Rime's phonetic alphabet used to specify custom pronunciations on Mist v1 and Mist v2.
- [Teams](https://docs.rime.ai/platform/teams.md): Create and manage Rime teams: invites, roles, billing, and member management.
- [Enterprise voice cloning](https://docs.rime.ai/platform/voice-cloning.md): Order an enterprise voice clone trained on Coda, Arcana, or Mist.

## OpenAPI Specs

- [openapi](https://docs.rime.ai/api-reference/openapi.json)