# LMNT Developer Documentation This file provides an overview of the LMNT API documentation and developer resources. ## Root URL LMNT Docs https://docs.lmnt.com ## Build ### First steps - [Intro to LMNT](https://docs.lmnt.com/intro.md): LMNT provides fast, lifelike, and affordable speech models. Our models excel at latency, voice cloning, accents, styles, languages, and more. - [Get started with LMNT](https://docs.lmnt.com/quickstart.md): Make your first API call to LMNT and build a simple storyteller. ### Building with LMNT - [Features overview](https://docs.lmnt.com/build-with-lmnt/overview.md): Explore LMNT's advanced features and capabilities. - [Using the Speech API](https://docs.lmnt.com/build-with-lmnt/speech-api.md): Practical patterns for using the Speech API effectively. - [Using the Speech Sessions API](https://docs.lmnt.com/build-with-lmnt/speech-sessions-api.md): Practical patterns for building realtime speech experiences using your favorite LLM + LMNT. - [Agentic coding tools](https://docs.lmnt.com/build-with-lmnt/agentic-coding-tools.md): Set up Claude Code, Codex, Augment Code, and other agentic coding tools to write LMNT integrations with up-to-date context. - [Optimizing latency](https://docs.lmnt.com/build-with-lmnt/optimizing-latency.md): Tips for getting latency down as low as possible with LMNT's speech models ### Model capabilities - [Voice cloning](https://docs.lmnt.com/build-with-lmnt/voice-cloning.md): Create voices to use with LMNT's models with 5-10 seconds of reference speech - [Accents](https://docs.lmnt.com/build-with-lmnt/accents.md): LMNT's speech models can generate any accent; plus - your options to change accents on the fly - [Languages](https://docs.lmnt.com/build-with-lmnt/languages.md): LMNT's speech models fluently speak 31 languages with native code-switching. - [Word timestamps](https://docs.lmnt.com/build-with-lmnt/word-timestamps.md): LMNT's models return word timestamps, enabling you to sync subtitles, lip movement, other modalities, and more with your generated speech. ### Prompt engineering - [Prompt engineering overview](https://docs.lmnt.com/prompt-engineering/overview.md) - [Voice prompting](https://docs.lmnt.com/prompt-engineering/voice-prompting.md): Comprehensive guide to voice prompt engineering for LMNT's latest models. - [Text prompting](https://docs.lmnt.com/prompt-engineering/text-prompting.md): Comprehensive guide to text prompt engineering for LMNT's latest models - [Getting LLMs to sound human](https://docs.lmnt.com/prompt-engineering/llm-prompting.md): Transform robotic LLM responses into natural, engaging speech ### Integrations #### LiveKit - [LiveKit + LMNT](https://docs.lmnt.com/integrations/livekit/introduction.md): Build production-grade multimodal voice AI agents with LiveKit, a realtime framework for voice, video, and data streaming applications. - [Quickstart](https://docs.lmnt.com/integrations/livekit/quickstart.md): Build and deploy your first LiveKit agent using LMNT for speech generation #### Pipecat - [Pipecat + LMNT](https://docs.lmnt.com/integrations/pipecat/introduction.md): Create an end-to-end conversational voice agent with Pipecat, an open-source Python framework built for real-time voice interactions. - [Installation & setup](https://docs.lmnt.com/integrations/pipecat/installation.md): Get Pipecat and its required services installed on your machine - [Quickstart](https://docs.lmnt.com/integrations/pipecat/quickstart.md): Build and run your first Pipecat application using LMNT - [Pipecat Cloud + LMNT Quickstart](https://docs.lmnt.com/integrations/pipecat/cloud-quickstart.md): Deploy your first Pipecat Cloud agent w/ LMNT TTS #### Vapi - [Vapi + LMNT](https://docs.lmnt.com/integrations/vapi/introduction.md): Create an end-to-end conversational voice agent with Vapi, a powerful platform for building and serving voice AI applications with real-time interactions. - [Web calling w/ Vapi + LMNT](https://docs.lmnt.com/integrations/vapi/quickstart.md): Make a web call to your assistant from the browser - [Vercel guide](https://docs.lmnt.com/integrations/vercel.md): Learn how to use LMNT in your Vercel apps. ### Release notes - [LMNT platform](https://docs.lmnt.com/release-notes/overview.md): Record of changes across our models and API surfaces. ## Models ### Models - [Models overview](https://docs.lmnt.com/models/overview.md): LMNT creates state-of-the-art speech models. This guide introduces the available models and compares their performance. ## Client SDKs ### Client SDKs - [Client SDKs](https://docs.lmnt.com/api/client-sdks.md): Official SDKs for using LMNT with Python and TypeScript. - [Python SDK](https://docs.lmnt.com/api/sdks/python.md): Install and configure the LMNT Python SDK with sync and async client support. - [TypeScript SDK](https://docs.lmnt.com/api/sdks/typescript.md): Install and configure the LMNT TypeScript SDK for Node.js, Deno, Bun, and Edge runtimes. ## API Reference ### Using the API - [API overview](https://docs.lmnt.com/api/overview.md) - [Errors](https://docs.lmnt.com/api/errors.md) ### Speech - [Speech](https://docs.lmnt.com/api/speech.md) - [Speech (Python)](https://docs.lmnt.com/api/python/speech.md) - [Speech (TypeScript)](https://docs.lmnt.com/api/typescript/speech.md) - [Generate speech](https://docs.lmnt.com/api/speech/generate.md): Generates speech from text and streams the audio as binary data chunks in real-time as they are generated. This is the recommended endpoint for most text-to-speech use cases. You can either stream the chunks for low-latency playback or collect all chunks to get the complete audio file. - [Generate speech (Python)](https://docs.lmnt.com/api/python/speech/generate.md) - [Generate speech (TypeScript)](https://docs.lmnt.com/api/typescript/speech/generate.md) - [Generate speech with timestamps](https://docs.lmnt.com/api/speech/generate-detailed.md): Generates speech from text and returns a JSON object that contains a base64-encoded audio string and optionally word-level timestamps. This endpoint waits for all speech to be generated before responding, so it is not ideal for latency-sensitive applications. - [Generate speech with timestamps (Python)](https://docs.lmnt.com/api/python/speech/generate-detailed.md) - [Generate speech with timestamps (TypeScript)](https://docs.lmnt.com/api/typescript/speech/generate-detailed.md) ### Speech Sessions - [Speech Sessions](https://docs.lmnt.com/api/speech-sessions.md) - [Speech Sessions (Python)](https://docs.lmnt.com/api/python/speech-sessions.md) - [Speech Sessions (TypeScript)](https://docs.lmnt.com/api/typescript/speech-sessions.md) - [Create speech session](https://docs.lmnt.com/api/speech-sessions/create.md): Stream text to our servers and receive generated speech in real-time. Great for latency-sensitive applications and situations where you don't have all the text upfront. - [Create speech session (Python)](https://docs.lmnt.com/api/python/speech-sessions/create.md) - [Create speech session (TypeScript)](https://docs.lmnt.com/api/typescript/speech-sessions/create.md) ### Voices - [Voices](https://docs.lmnt.com/api/voices.md) - [Voices (Python)](https://docs.lmnt.com/api/python/voices.md) - [Voices (TypeScript)](https://docs.lmnt.com/api/typescript/voices.md) - [Create voice](https://docs.lmnt.com/api/voices/create.md): Submits a request to create a voice with a supplied voice configuration and a batch of input audio data. - [Create voice (Python)](https://docs.lmnt.com/api/python/voices/create.md) - [Create voice (TypeScript)](https://docs.lmnt.com/api/typescript/voices/create.md) - [List voices](https://docs.lmnt.com/api/voices/list.md): Returns a list of voices available to you. - [List voices (Python)](https://docs.lmnt.com/api/python/voices/list.md) - [List voices (TypeScript)](https://docs.lmnt.com/api/typescript/voices/list.md) - [Retrieve voice](https://docs.lmnt.com/api/voices/retrieve.md): Returns details of a specific voice. - [Retrieve voice (Python)](https://docs.lmnt.com/api/python/voices/retrieve.md) - [Retrieve voice (TypeScript)](https://docs.lmnt.com/api/typescript/voices/retrieve.md) - [Update voice](https://docs.lmnt.com/api/voices/update.md): Updates metadata for a specific voice. Only provided fields will be changed. - [Update voice (Python)](https://docs.lmnt.com/api/python/voices/update.md) - [Update voice (TypeScript)](https://docs.lmnt.com/api/typescript/voices/update.md) - [Delete voice](https://docs.lmnt.com/api/voices/delete.md): Deletes a voice and cancels any pending operations on it. Cannot be undone. - [Delete voice (Python)](https://docs.lmnt.com/api/python/voices/delete.md) - [Delete voice (TypeScript)](https://docs.lmnt.com/api/typescript/voices/delete.md) ### Accounts - [Accounts](https://docs.lmnt.com/api/accounts.md) - [Accounts (Python)](https://docs.lmnt.com/api/python/accounts.md) - [Accounts (TypeScript)](https://docs.lmnt.com/api/typescript/accounts.md) - [Retrieve account](https://docs.lmnt.com/api/accounts/retrieve.md): Returns details about your account. - [Retrieve account (Python)](https://docs.lmnt.com/api/python/accounts/retrieve.md) - [Retrieve account (TypeScript)](https://docs.lmnt.com/api/typescript/accounts/retrieve.md) ### Support & configuration - [Versions](https://docs.lmnt.com/api/versioning.md) --- For more comprehensive documentation, see [llms-full.txt](https://docs.lmnt.com/llms-full.txt)