# KugelAudio

## Docs

- [Authentication](https://docs.kugelaudio.com/api-reference/authentication.md): How to authenticate with the KugelAudio API
- [Dictionaries](https://docs.kugelaudio.com/api-reference/endpoints/dictionaries.md): Manage per-project custom word dictionaries
- [Models](https://docs.kugelaudio.com/api-reference/endpoints/models.md): List available TTS models
- [Voices](https://docs.kugelaudio.com/api-reference/endpoints/voices.md): Manage and list voices
- [Error Codes](https://docs.kugelaudio.com/api-reference/errors.md): Lookup table for KugelAudio TTS API error responses
- [API Reference](https://docs.kugelaudio.com/api-reference/introduction.md): Complete API documentation for KugelAudio
- [Use the API without an SDK](https://docs.kugelaudio.com/api-reference/raw-api.md): Base URL, authentication forms, and tooling for calling the KugelAudio API directly.
- [Audio Formats](https://docs.kugelaudio.com/api-reference/tts/audio-formats.md): Output encodings, the output_format token, G.711 telephony codecs, audio chunk fields, and the AI watermark.
- [Generate Speech](https://docs.kugelaudio.com/api-reference/tts/generate.md): REST endpoint: POST /v1/tts/generate — one request, streamed PCM response.
- [Multi-Context Streaming](https://docs.kugelaudio.com/api-reference/tts/multi-context.md): WebSocket endpoint: /ws/tts/multi — up to 20 independent audio streams over one connection.
- [Stream Speech](https://docs.kugelaudio.com/api-reference/tts/stream.md): WebSocket endpoint: /ws/tts — one request, audio chunks streamed back, ends with a final message.
- [Stream Input](https://docs.kugelaudio.com/api-reference/tts/stream-input.md): WebSocket endpoint: /ws/tts/stream — token-by-token text input, turn-based sessions for LLM agents.
- [Dictionaries](https://docs.kugelaudio.com/features/dictionaries.md): Control pronunciations for brand names, acronyms, and domain vocabulary
- [Generate Speech](https://docs.kugelaudio.com/features/generate.md): Generate high-quality speech from text using KugelAudio
- [Text Normalization & Spelling](https://docs.kugelaudio.com/features/text-processing.md): Control how text is processed before speech synthesis
- [Voice Cloning](https://docs.kugelaudio.com/features/voice-cloning.md): Create custom voices from audio samples
- [Using Voices](https://docs.kugelaudio.com/features/voices.md): Browse, filter, and use voices for speech generation
- [Regions](https://docs.kugelaudio.com/guides/regions.md): Choose between the canonical endpoint and the direct EU endpoint
- [Self-Hosted Deployment](https://docs.kugelaudio.com/guides/self-hosted.md): Run KugelAudio TTS on your own infrastructure
- [Voice Agent Prompting](https://docs.kugelaudio.com/guides/voice-prompting.md): Copy-paste prompt patterns for LLM-driven voice agents — structure, disfluency, guardrails, tools
- [Welcome to KugelAudio](https://docs.kugelaudio.com/index.md): High-quality, low-latency text-to-speech for real-time applications
- [ElevenLabs API Compatibility](https://docs.kugelaudio.com/integrations/elevenlabs-proxy.md): Use KugelAudio with any ElevenLabs-compatible SDK or integration
- [LiveKit Integration](https://docs.kugelaudio.com/integrations/livekit.md): Use KugelAudio TTS with the LiveKit Agents framework
- [PipeCat Integration](https://docs.kugelaudio.com/integrations/pipecat.md): Use KugelAudio TTS with the PipeCat voice AI framework
- [Vapi Integration](https://docs.kugelaudio.com/integrations/vapi.md): Use KugelAudio as a custom TTS provider in Vapi voice assistants
- [Latency](https://docs.kugelaudio.com/latency.md): What determines time-to-first-audio (TTFA), what numbers to expect, and the levers that lower them.
- [Models](https://docs.kugelaudio.com/models.md): Available TTS models and legacy model IDs
- [Breaks](https://docs.kugelaudio.com/prompting/breaks.md): Insert explicit pauses with SSML-style break tags — syntax, accepted values, and how durations are snapped.
- [Prompting overview](https://docs.kugelaudio.com/prompting/overview.md): How to shape speech output through text — what's supported, writing tips, and what to avoid.
- [Pronunciation & IPA](https://docs.kugelaudio.com/prompting/pronunciation.md): Fix how specific words are spoken — inline IPA in the request text, or replacement/IPA entries in pronunciation dictionaries.
- [Speed](https://docs.kugelaudio.com/prompting/speed.md): Pitch-preserving rate control — globally via the speed parameter, per span via <prosody rate> tags.
- [Spell tags](https://docs.kugelaudio.com/prompting/spell.md): Character-by-character pronunciation for emails, codes, acronyms, and serial numbers — including grouped spelling.
- [Quick Start](https://docs.kugelaudio.com/quickstart.md): Get started with KugelAudio in under 5 minutes
- [Configuration](https://docs.kugelaudio.com/sdks/java/configuration.md): Client options, authentication modes, and region selection
- [Dictionaries](https://docs.kugelaudio.com/sdks/java/dictionaries.md): Per-project pronunciation and replacement lists for consistent brand and domain vocabulary
- [Generate & Stream](https://docs.kugelaudio.com/sdks/java/generate.md): One-shot generation, streaming audio, text normalization, word timestamps, and error handling
- [LLM Sessions](https://docs.kugelaudio.com/sdks/java/llm-sessions.md): Streaming sessions for LLM token streams, barge-in, session reuse, and multi-context sessions
- [Quickstart](https://docs.kugelaudio.com/sdks/java/quickstart.md): Install the KugelAudio Java SDK and generate your first audio
- [Types](https://docs.kugelaudio.com/sdks/java/types.md): Data models, audio utilities, and a complete end-to-end example
- [Voices](https://docs.kugelaudio.com/sdks/java/voices.md): List, create, update, and manage voices and their reference audio
- [Client Configuration](https://docs.kugelaudio.com/sdks/javascript/configuration.md): Configure the KugelAudio client — options, authentication modes, regions, and lifecycle
- [Dictionaries](https://docs.kugelaudio.com/sdks/javascript/dictionaries.md): Per-project pronunciation and replacement lists for brand names and domain vocabulary
- [Generate Audio](https://docs.kugelaudio.com/sdks/javascript/generate.md): One-shot generation, streamed audio output, word timestamps, models, and audio utilities
- [Quickstart](https://docs.kugelaudio.com/sdks/javascript/quickstart.md): Install the KugelAudio JavaScript SDK, set up the client, and generate your first audio
- [Streaming Sessions](https://docs.kugelaudio.com/sdks/javascript/streaming.md): Persistent WebSocket sessions for LLM pipelines — chunking, session reuse, barge-in, and multi-context
- [Text Normalization](https://docs.kugelaudio.com/sdks/javascript/text-normalization.md): Convert numbers, dates, and symbols into spoken words, with language hints and spell tags
- [Types & Errors](https://docs.kugelaudio.com/sdks/javascript/types.md): Error classes and the full TypeScript interface reference for the KugelAudio SDK
- [Voices](https://docs.kugelaudio.com/sdks/javascript/voices.md): List, create, update, publish, and manage voices and their reference audio
- [Configuration](https://docs.kugelaudio.com/sdks/python/configuration.md): Client options, lifecycle, and region selection
- [Dictionaries](https://docs.kugelaudio.com/sdks/python/dictionaries.md): Per-project pronunciation and replacement lists
- [Generate Speech](https://docs.kugelaudio.com/sdks/python/generate.md): One-shot speech generation, generation parameters, models, and word timestamps
- [Text Normalization](https://docs.kugelaudio.com/sdks/python/normalization.md): Convert numbers, dates, and symbols to spoken words, with spell tags
- [Quickstart](https://docs.kugelaudio.com/sdks/python/quickstart.md): Install the KugelAudio Python SDK and generate your first audio
- [Streaming](https://docs.kugelaudio.com/sdks/python/streaming.md): Streaming audio, LLM streaming sessions, barge-in, and multi-context sessions
- [Types & Errors](https://docs.kugelaudio.com/sdks/python/types.md): Exceptions, data models, and enums exported by the SDK
- [Voices](https://docs.kugelaudio.com/sdks/python/voices.md): List, create, update, and manage voices and reference audio
- [Barge-in](https://docs.kugelaudio.com/streaming/barge-in.md): Cancel the current turn immediately when the user interrupts — without closing the WebSocket.
- [Chunking & per-segment latency](https://docs.kugelaudio.com/streaming/chunking-and-latency.md): How server-side chunking works, why client-side flushing destroys TTFA, and the knobs that tune both.
- [Multi-context streaming](https://docs.kugelaudio.com/streaming/multi-context.md): Manage up to 20 independent audio streams over a single WebSocket connection.
- [Streaming overview](https://docs.kugelaudio.com/streaming/overview.md): Stream audio as it's generated — the patterns, the four rules that keep latency low, and audio playback.
- [Turn lifecycle](https://docs.kugelaudio.com/streaming/turn-lifecycle.md): What a turn is, how it starts and ends, session reuse across turns, and per-session usage reporting.
- [Word timestamps](https://docs.kugelaudio.com/streaming/word-timestamps.md): Word-level time alignments delivered alongside streaming audio — for barge-in handling, subtitles, and lip-sync.

## OpenAPI Specs

- [openapi](https://docs.kugelaudio.com/api-reference/openapi.json)

## Optional

- [GitHub](https://github.com/kugelaudio)