# upliftai.org

> AI-optimized mirror of upliftai.org containing 53 pages totalling 23,800 words of clean markdown content, structured data, and semantic HTML. Original source: https://upliftai.org. Last updated: 2026-07-21T07:42:51.241Z.

Each page is available as HTML (with JSON-LD structured data) and Markdown (text-only, ideal for LLMs and RAG).

## Homepage

- [Uplift AI](/content/platform/index.html) (56 words)
- [docs/index.html](/content/docs/index.html) (289 words)
- [Uplift AI - Voice Models for Pakistani Languages](/content/site-root.html): State of the art speech generation and speech understanding models for Pakistani Languages. (235 words)

## Articles & Blog Posts

- [Uplift AI - Voice Models for Pakistani Languages](/content/calling/index.html): State of the art speech generation and speech understanding models for Pakistani Languages. (31 words)
- [Uplift AI - Voice Models for Pakistani Languages](/content/studio/index.html): State of the art speech generation and speech understanding models for Pakistani Languages. (958 words)
- [Async Streaming Text to Speech - Uplift AI API Docs](/content/docs/api-reference/endpoint/text-to-speech-stream-async/index.html): Asynchronous streaming text-to-speech for direct client delivery This endpoint initiates streaming text-to-speech synthesis and immediately returns a mediaId and token. Unlike regular async TTS, this enables chunked streaming with ~300ms first chunk latency when retrieved. When to use this endpoint: - Frontend streaming - Stream audio directly to browsers without proxy - Low-latency playback - Start playing audio before full generation completes - CDN streaming - Progressive download through content delivery networks - Mobile apps - Reduce initial buffering time For best results with Urdu, use Urdu script. For English words within Urdu text, use ASCII characters. Example: "یہ ایک exerted force ہے" The audio streams progressively when retrieved via the /stream-audio endpoint. (483 words)
- [Stream Text to Speech - Uplift AI API Docs](/content/docs/api-reference/endpoint/text-to-speech-stream/index.html): Converts the provided text to speech audio using the specified voice, response is streamed with "Transfer-Encoding" "chunked" header. We currently aim the p90 first chunk latency to be around 300ms in Pakistan, we are also actively working reducing this. For best results, we expect you to use Urdu script. To get better pronounciation of English words, use ASCII characters for them. Example "یہ ایک exerted force ہے" Returns the audio data directly in the response. (454 words)
- [Async Text to Speech - Uplift AI API Docs](/content/docs/api-reference/endpoint/text-to-speech-async/index.html): Asynchronous text-to-speech synthesis for bot and server-side workflows This endpoint initiates text-to-speech synthesis and immediately returns a mediaId and token. The audio is generated asynchronously and can be retrieved using the returned credentials. When to use this endpoint: - Bot integrations (WhatsApp, Telegram, etc.) - Avoid audio passing through your system - Webhook workflows - When you need to process audio generation separately - Batch processing - When converting multiple texts without blocking - Direct client delivery - Let clients fetch audio directly using the secure token For best results with Urdu, use Urdu script. For English words within Urdu text, use ASCII characters. Example: "یہ ایک exerted force ہے" The generated audio URL can be shared directly with end users or services without proxying through your server. (491 words)
- [Update Phrase Replacement Config - Uplift AI API Docs](/content/docs/api-reference/endpoint/update-phrase-replacement-config/index.html): Update an existing phrase replacement configuration Updates an existing phrase replacement configuration with new phrase replacements. (284 words)
- [Get Phrase Replacement Config - Uplift AI API Docs](/content/docs/api-reference/endpoint/get-phrase-replacement-config/index.html): Get a specific phrase replacement configuration Retrieves a specific phrase replacement configuration by its ID. (283 words)
- [Retrieve Async Audio - Uplift AI API Docs](/content/docs/api-reference/endpoint/stream-audio/index.html): Retrieve audio generated by async text-to-speech endpoints This endpoint retrieves audio files generated by both async TTS endpoints. Requires the mediaId and JWT token returned from the async synthesis request. Behavior depends on the originating endpoint: From /text-to-speech-async: - Returns complete audio file when ready - Typically available within 1-2 seconds - Best for bots and webhooks needing complete files From /text-to-speech/stream-async: - Supports chunked streaming with ~300ms first chunk latency - Audio streams progressively as it's generated - Best for frontend apps and real-time playback Key features: - Direct access - Can be accessed directly by clients without your API key - Secure - JWT token ensures only authorized access to the audio - CDN-ready - Optimized for content delivery networks (238 words)
- [Terms of Service — Uplift AI](/content/platform/terms-of-service/index.html): Terms of Service for Uplift AI and Orator Studio services. (2,037 words)
- [Voices - Uplift AI API Docs](/content/docs/orator_voices/index.html): Built to sound like Pakistan. 82 native voices — every accent, every walk of life. (1,095 words)
- [Create Phrase Replacement Config - Uplift AI API Docs](/content/docs/api-reference/endpoint/create-phrase-replacement-config/index.html): Create a new phrase replacement configuration Creates a new configuration for phrase replacements that can be applied during text-to-speech synthesis. (343 words)
- [docs/tutorials/index.html](/content/docs/tutorials/index.html) (588 words)
- [Privacy Policy — Uplift AI](/content/platform/privacy-policy/index.html): Privacy Policy for Uplift AI and Orator Studio services. (1,525 words)
- [Page Not Found](/content/docs/assistants/deployment/index.html) (28 words)
- [Text to Speech - Uplift AI API Docs](/content/docs/api-reference/endpoint/text-to-speech/index.html): Converts the provided text to speech audio using the specified voice. For best results, we expect you to use Urdu script. To get better pronounciation of English words, use ASCII characters for them. Example "یہ ایک exerted force ہے" Returns the audio data directly in the response. (320 words)
- [WebSocket TTS API - Uplift AI API Docs](/content/docs/websocket-tts/index.html): Real-time text-to-speech streaming for conversational AI (574 words)
- [Async TTS Concepts - Uplift AI API Docs](/content/docs/async-concepts/index.html): Understanding synchronous vs asynchronous text-to-speech (437 words)
- [Page Not Found](/content/docs/assistants/quickstart/index.html) (27 words)
- [Page Not Found](/content/docs/assistants/dynamic-configuration/index.html) (26 words)
- [List Phrase Replacement Configs - Uplift AI API Docs](/content/docs/api-reference/endpoint/list-phrase-replacement-configs/index.html): List all phrase replacement configurations Returns a list of all phrase replacement configurations for the current organization and project. (244 words)
- [Welcome to Uplift AI - Uplift AI API Docs](/content/docs/introduction/index.html): Build voice-powered applications with state-of-the-art Urdu TTS (313 words)
- [docs/llms-txt.html](/content/docs/llms-txt.html) (281 words)
- [Request Limits - Uplift AI API Docs](/content/docs/orator_limits/index.html) (66 words)
- [Build Your First Voice Assistant - Uplift AI API Docs](/content/docs/assistants/tutorial/index.html): Create a realtime voice assistant with React in 10 minutes (1,373 words)
- [React SDK Reference - Uplift AI API Docs](/content/docs/assistants/sdk/react/index.html): Complete reference for @upliftai/assistants-react (880 words)
- [Speech to Text (Beta) - Uplift AI API Docs](/content/docs/api-reference/endpoint/speech-to-text/index.html): Transcribe audio files to text using AI models Converts audio files to text using Uplift's speech recognition models optimized for Urdu language. Model Selection: - scribe: Full accuracy model - 40 credits per minute - scribe-mini: Cost-effective model - 20 credits per minute (50% cheaper) Domain Optimization: Use the domain parameter for improved accuracy in specialized contexts: - phone-commerce: Optimized for e-commerce conversations - farming: Optimized for agricultural terminology (375 words)
- [Quickstart Guide - Uplift AI API Docs](/content/docs/orator/index.html): High-quality Pakistani text-to-speech with natural pronunciation (748 words)
- [WebSocket TTS for Conversational AI - Uplift AI API Docs](/content/docs/tutorials/websocket-conversational-ai/index.html): Build real-time voice agents with streaming text-to-speech (817 words)
- [WhatsApp Voice Bot Tutorial - Uplift AI API Docs](/content/docs/tutorials/whatsapp-bot/index.html): Build a voice-enabled WhatsApp bot with Uplift AI TTS (564 words)
- [Create Adhoc Session - Uplift AI API Docs](/content/docs/assistants/api-reference/create-adhoc-session/index.html): Create a temporary session with custom configuration (653 words)
- [Building Custom Tools - Uplift AI API Docs](/content/docs/assistants/tools/index.html): Extend your assistant with powerful custom functions (812 words)
- [Create Realtime Assistant - Uplift AI API Docs](/content/docs/assistants/api-reference/create-assistant/index.html): Create a new realtime assistant configuration (412 words)
- [LiveKit Voice Agent - Uplift AI API Docs](/content/docs/tutorials/livekit-voice-agent/index.html): Build a Pakistan History voice assistant in 5 minutes (551 words)
- [Core Concepts - Uplift AI API Docs](/content/docs/assistants/concepts/index.html): Understanding the building blocks of Realtime Assistants (680 words)
- [Phrase Replacements - Uplift AI API Docs](/content/docs/sdk/nodejs/phrase-replacements/index.html): Control pronunciation of brand names, technical terms, and LLM outputs (190 words)
- [WebSocket Text to Speech - Uplift AI API Docs](/content/docs/sdk/nodejs/websocket-tts/index.html): Real-time multiplexed TTS streaming with client.tts.connect() (448 words)
- [Update Realtime Assistant - Uplift AI API Docs](/content/docs/assistants/api-reference/update-assistant/index.html): Update an existing realtime assistant configuration (385 words)
- [Realtime Assistants Overview - Uplift AI API Docs](/content/docs/assistants/introduction/index.html): Build powerful voice AI assistants with real-time conversation capabilities (540 words)
- [Realtime Voice Assistants - Uplift AI API Docs](/content/docs/realtime-assistants-intro/index.html): Build conversational AI agents with UpliftAI (251 words)
- [Create Public Session - Uplift AI API Docs](/content/docs/assistants/api-reference/create-public-session/index.html): Create a session for a public assistant without authentication (399 words)
- [List Realtime Assistants - Uplift AI API Docs](/content/docs/assistants/api-reference/list-assistants/index.html): List all realtime assistants in your organization (210 words)
- [Getting Started - Uplift AI API Docs](/content/docs/sdk/nodejs/overview/index.html): Official Node.js SDK for the Uplift AI API (189 words)
- [Stream Text to Speech - Uplift AI API Docs](/content/docs/sdk/nodejs/text-to-speech-stream/index.html): HTTP streaming with client.tts.createStream() for low-latency playback (196 words)
- [Speech to Text - Uplift AI API Docs](/content/docs/sdk/nodejs/speech-to-text/index.html): Transcribe audio files with client.stt.transcribe() (161 words)
- [Get Realtime Assistant - Uplift AI API Docs](/content/docs/assistants/api-reference/get-assistant/index.html): Retrieve a specific realtime assistant configuration (209 words)
- [Error Handling - Uplift AI API Docs](/content/docs/sdk/nodejs/error-handling/index.html): Typed errors and retry behavior in the Node.js SDK (216 words)
- [Async Text to Speech - Uplift AI API Docs](/content/docs/sdk/nodejs/text-to-speech-async/index.html): Background TTS jobs with pre-signed URLs using client.tts.enqueue() (291 words)
- [Text to Speech - Uplift AI API Docs](/content/docs/sdk/nodejs/text-to-speech/index.html): Generate complete audio buffers with client.tts.create() (133 words)
- [Create Session - Uplift AI API Docs](/content/docs/assistants/api-reference/create-session/index.html): Create a new session for connecting to a realtime assistant (273 words)
- [Delete Realtime Assistant - Uplift AI API Docs](/content/docs/assistants/api-reference/delete-assistant/index.html): Delete a realtime assistant configuration (138 words)

## Resources

- [Full Page Index](/index.html): Browse all cached pages with rich metadata
- [About This Cache](/content/about.html): Methodology, technical details, and usage guidelines
- [XML Sitemap](/sitemap.xml): Machine-readable sitemap for crawler discovery
- [Robots.txt](/robots.txt): Crawler directives