# Camb.ai

## Docs

- [Add Term to Dictionary](https://docs.camb.ai/api-reference/endpoint/add-term-to-dictionary.md): Adds a new term and its translations to an existing dictionary, enabling you to expand your multilingual terminology database with precise linguistic mappings.
- [Create Audio Separation](https://docs.camb.ai/api-reference/endpoint/create-audio-separation.md): Creates a task to separate an audio file into distinct background and foreground components
- [Create a Custom Voice](https://docs.camb.ai/api-reference/endpoint/create-custom-voice.md): Creates a new voice clone by uploading an audio file reference.
- [Create a Dictionary From File](https://docs.camb.ai/api-reference/endpoint/create-dictionary-from-file.md): This endpoint empowers you to build custom pronunciation and terminology dictionaries by uploading structured data files directly into your CAMB.AI workspace.
- [Create Folder](https://docs.camb.ai/api-reference/endpoint/create-folder.md): Establish organizational containers within your CAMB.AI workspace to structure audiobook projects effectively. This endpoint creates the foundational filing system that enables efficient project management and team collaboration across your growing content library.
- [Setup Project](https://docs.camb.ai/api-reference/endpoint/create-project-setup.md): Initialize dubbing projects through the API for seamless editing and management in CAMB.AI Studio. This endpoint creates the foundation for your dubbing workflow by analyzing source media and establishing optimal configuration parameters.
- [Create Story](https://docs.camb.ai/api-reference/endpoint/create-story.md): Creates a story based on the content provided in a text file (`.txt`) or Word document (`.docx`)
- [Setup Story](https://docs.camb.ai/api-reference/endpoint/create-story-setup.md): Initialize audiobook projects through the API for seamless editing and management in CAMB.AI Studio. This endpoint creates the foundation for your stories workflow by analyzing source text and establishing optimal narration parameters.
- [Create Sound and Music](https://docs.camb.ai/api-reference/endpoint/create-text-to-sound.md): Creates a task to generate an audio file—either music or sound effects—from a given text prompt
- [Create Voice from Description](https://docs.camb.ai/api-reference/endpoint/create-text-to-voice.md): Submits a request to initiate a task for creating a human-like voice from a given text prompt.
- [Create Transcription](https://docs.camb.ai/api-reference/endpoint/create-transcription.md): Creates a task to process speech into readable text. Submit either an media file or a publicly accessible media URL.
- [Create Translated Story](https://docs.camb.ai/api-reference/endpoint/create-translated-story.md): Creates a translated story based on a previously generated story using the provided `run_id`
- [Create Translated Text-to-Speech](https://docs.camb.ai/api-reference/endpoint/create-translated-tts.md): Creates a task to translate input text and generate corresponding speech audio
- [Create Translation](https://docs.camb.ai/api-reference/endpoint/create-translation.md): Translate text into multiple languages with customizable settings for formality, gender, and specialized vocabulary to meet your global communication needs.
- [Create Translation Stream](https://docs.camb.ai/api-reference/endpoint/create-translation-stream.md): Deprecated: Convert text between languages in real-time with contextual adaptations, delivering translated content as it's generated for immediate use in conversational interfaces and live applications.
- [Create Text-to-Speech](https://docs.camb.ai/api-reference/endpoint/create-tts.md): Convert text to natural-sounding speech with customizable voice settings, allowing you to generate audio files for playback in your applications.
- [Stream Text-to-Speech Audio](https://docs.camb.ai/api-reference/endpoint/create-tts-stream.md): Convert text to speech in real-time with customizable voice characteristics, delivering audio content as it's generated for immediate playback in your applications.
- [Delete a Dictionary](https://docs.camb.ai/api-reference/endpoint/delete-dictionary.md): Permanently removes a dictionary and all its associated terms and translations from the system. This irreversible action completely eliminates the dictionary's data and cannot be undone.
- [Delete a Term in Dictionary](https://docs.camb.ai/api-reference/endpoint/delete-term-in-dictionary.md): Permanently removes a specific term and all its associated translations from a dictionary, providing precise control over dictionary content while maintaining the integrity of remaining terms.
- [Delete a Voice](https://docs.camb.ai/api-reference/endpoint/delete-voice.md): Permanently deletes a custom voice from your workspace using its voice ID.
- [End to End Dubbing](https://docs.camb.ai/api-reference/endpoint/end-to-end-dubbing.md): Initiate a full end to end dubbing task.
- [Get Audio Separation Run Results (Bulk)](https://docs.camb.ai/api-reference/endpoint/fetch-audio-separation-run-info-results.md): Retrieve separated audio components for multiple completed Audio Separation tasks using multiple run IDs.
- [Fetch Dubbing Results in Bulk](https://docs.camb.ai/api-reference/endpoint/fetch-dubbed-runs-info.md): Retrieves the results of multiple dubbing runs simultaneously using an array of `run_id` values
- [Fetch Project Setup Results](https://docs.camb.ai/api-reference/endpoint/fetch-project-setup-runs-results.md): Retrieve comprehensive setup results for multiple localization projects in a single API call, streamlining project management in CAMB.AI Studio.
- [Fetch Stories Results in Bulk](https://docs.camb.ai/api-reference/endpoint/fetch-stories-runs-info.md): Efficiently retrieve multiple story conversion outputs simultaneously using a collection of run identifiers
- [Fetch Sound and Music Run Results (Bulk)](https://docs.camb.ai/api-reference/endpoint/fetch-text-to-sound-runs-results.md): Retrieve multiple generated audio files for completed Sound and Music tasks using multiple run IDs.
- [Fetch Transcription Results](https://docs.camb.ai/api-reference/endpoint/fetch-transcriptions-runs-results.md): Retrieves the results of multiple transcription runs using the provided run IDs in the request body.
- [Fetch Translation Results in Bulk](https://docs.camb.ai/api-reference/endpoint/fetch-translation-runs-results.md): Retrieves the final translated texts from multiple completed translation tasks using a list of `run_id` values in a single request.
- [Fetch Bulk Text-to-Speech Results](https://docs.camb.ai/api-reference/endpoint/fetch-tts-runs-results.md): Retrieves the results of multiple Text-to-Speech runs using a list of `run_id` values in a single request.
- [Get Audio Separation Result](https://docs.camb.ai/api-reference/endpoint/get-audio-separation-run-info.md): Retrieves detail information about a specific audio separation run using the provided `run_id`.
- [Get Audio Separation Task Status](https://docs.camb.ai/api-reference/endpoint/get-audio-separation-status.md): Retrieves the current status of an audio separation task using the specified `task_id`.
- [Get Dictionary Full Details](https://docs.camb.ai/api-reference/endpoint/get-dictionary-full-details.md): Retrieves comprehensive details for a specific dictionary, including all terms and their definitions. Supports optional filtering and pagination to help you find exactly what you need.
- [Get Dictionary Summary](https://docs.camb.ai/api-reference/endpoint/get-dictionary-summary.md): Retrieves essential information about a specific dictionary, including its name, description, and metadata. Perfect for getting a quick overview without loading all dictionary terms.
- [Get Dubbed Output in Alt Format](https://docs.camb.ai/api-reference/endpoint/get-dub-alt-format.md): Fetches the dubbed output for a specified `run_id` and `language` in the file format that is provided in the request body.
- [Get Dubbed Output in Alt Format Task Status](https://docs.camb.ai/api-reference/endpoint/get-dub-alt-format-task-status.md): Retrieves the current status of a task exporting dubbed media to alternative file formats using the specified `task_id`.
- [Get Dubbing Transcript](https://docs.camb.ai/api-reference/endpoint/get-dub-transcript.md): Retrieves the transcript in the specified language of a specific end to end dubbing run using the provided `run_id`.
- [Get Dubbing Result](https://docs.camb.ai/api-reference/endpoint/get-dubbed-run-info.md): Retrieves the result of a specific end to end dubbing run using the provided `run_id`.
- [Get End to End Dubbing Task Status](https://docs.camb.ai/api-reference/endpoint/get-end-to-end-dubbing-status.md): Retrieves the current status of a Dubbing task using the specified `task_id`.
- [Get Project Setup Result](https://docs.camb.ai/api-reference/endpoint/get-project-setup-run-result.md): Retrieves the comprehensive results of a completed project setup process, providing detailed information about your prepared project and its readiness for editing in CAMB.AI Studio.
- [Get Project Setup Task Status](https://docs.camb.ai/api-reference/endpoint/get-project-setup-status.md): Monitor the progress and completion status of your project setup tasks. This endpoint provides real-time insights into the preparation process, helping you understand when your project becomes ready for editing in CAMB.AI Studio.
- [Get all Source Languages](https://docs.camb.ai/api-reference/endpoint/get-source-languages.md): Retrieves a comprehensive list of all source languages supported by the platform, including their unique identifiers, language names, and corresponding short names.
- [Retrieve Story Results](https://docs.camb.ai/api-reference/endpoint/get-story-run-info.md): Access completed story conversion outputs and transcripts using the unique run identifier
- [Get Story Task Status](https://docs.camb.ai/api-reference/endpoint/get-story-status.md): Retrieves the current status of a story task using the specified `task_id`.
- [Get all Target Languages](https://docs.camb.ai/api-reference/endpoint/get-target-languages.md): Retrieves a comprehensive list of all target languages supported by the platform, including their unique identifiers, language names, and corresponding short names.
- [Get Sound and Music Run Result](https://docs.camb.ai/api-reference/endpoint/get-text-to-sound-run-result.md): Retrieve the generated audio file for a completed Sound and Music task.
- [Get Sound and Music Task Status](https://docs.camb.ai/api-reference/endpoint/get-text-to-sound-status.md): Checks the current status of a sound and music generation task by querying with the provided `task_id`.
- [Get Voice from Description Result](https://docs.camb.ai/api-reference/endpoint/get-text-to-voice-run-result.md): Retrieve AI-generated voice interpretations and select your preferred vocal style from multiple audio options using `run_id`.
- [Get Voice from Description Task Status](https://docs.camb.ai/api-reference/endpoint/get-text-to-voice-status.md): Monitor the progress of your AI-generated voice creation through real-time status updates.
- [Get Transcription Result](https://docs.camb.ai/api-reference/endpoint/get-transcription-run-result.md): Retrieves the result of the transcription run using the provided `run_id`.
- [Get Translated Story Result](https://docs.camb.ai/api-reference/endpoint/get-translated-story-run-result.md): Retrieves detailed results about a specific translated story using the provided `run_id` and `target_language` parameters.
- [Get Translated Story Status](https://docs.camb.ai/api-reference/endpoint/get-translated-story-status.md): Retrieves the current status of a story translation task using the specified `task_id`.
- [Get Translation Result](https://docs.camb.ai/api-reference/endpoint/get-translation-run-result.md): Retrieves the final translated texts from a completed translation task using the provided `run_id`.
- [Get Text-to-Speech Task Status](https://docs.camb.ai/api-reference/endpoint/get-tts-result.md): Retrieves the current status of a Text-to-Speech task using the specified `task_id`.
- [Get Text-to-Speech Result](https://docs.camb.ai/api-reference/endpoint/get-tts-run-info.md): Retrieves the result of a specific Text-to-Speech run using the provided `run_id`.
- [List Dictionaries](https://docs.camb.ai/api-reference/endpoint/list-dictionaries.md): Retrieve all dictionaries available in the workspace associated with your API key.
- [List Folders](https://docs.camb.ai/api-reference/endpoint/list-folders.md): The List Folders endpoint provides comprehensive access to your organizational structure within the CAMB.AI workspace, allowing you to retrieve and explore the folders that serve as containers for your audio processing projects. This endpoint becomes increasingly valuable as your workspace grows, of…
- [List all Voices](https://docs.camb.ai/api-reference/endpoint/list-voices.md): Retrieves a comprehensive list of all available voices, including public voices, shared voices, and custom-created voices. Each voice entry provides detailed attributes such as a unique identifier, voice name, gender, and age, ensuring precise selection and usability.
- [Get Transcription Task Status](https://docs.camb.ai/api-reference/endpoint/poll-transcription-result.md): Retrieves the current status of a transcription task using the specified `task_id`.
- [Get Translated Text-to-Speech Status](https://docs.camb.ai/api-reference/endpoint/poll-translated-tts-result.md): Monitors the progress of a Translated Text-to-Speech task using the provided `task_id`.
- [Get Translation Task Status](https://docs.camb.ai/api-reference/endpoint/poll-translation-result.md): Monitor the progress of your translation tasks with real-time status updates, enabling you to track completion and retrieve translated content when ready.
- [Update Translation for a Term in Dictionary](https://docs.camb.ai/api-reference/endpoint/update-term-in-dictionary.md): Updates existing translations for a specific term within a dictionary, allowing you to refine translation accuracy, add new language variants, or correct linguistic content as your understanding evolves.
- [Choosing a Model](https://docs.camb.ai/choosing-a-model.md): A guide to picking the right MARS 8 variant for your use case
- [Custom Cloud Providers](https://docs.camb.ai/custom-cloud-providers.md)
- [Authentication & API Keys](https://docs.camb.ai/getting-started/authentication.md): Learn how to authenticate with the CAMB.AI API
- [Baseten](https://docs.camb.ai/hosting-platforms/baseten.md): Use Camb.ai MARS models with your own Baseten deployment
- [LiveKit](https://docs.camb.ai/integrations/livekit.md): Build real-time voice AI agents with Camb.ai TTS and LiveKit Agents
- [Pipecat](https://docs.camb.ai/integrations/pipecat.md): Build real-time voice AI agents with Camb.ai TTS and Pipecat
- [Introduction](https://docs.camb.ai/introduction.md)
- [MARS 8 TTS Models](https://docs.camb.ai/models.md)
- [Open Source](https://docs.camb.ai/open-source.md): Explore our state-of-the-art open source speech models.
- [Release Logs](https://docs.camb.ai/release-logs/overview.md): Track updates and improvements to CAMB.AI
- [General Guide](https://docs.camb.ai/sdk-guides/general-guide.md): Overview of Camb AI SDK concepts, architecture, and core components.
- [Go SDK Quickstart](https://docs.camb.ai/sdk-guides/go-sdk-quickstart.md)
- [Java SDK Quickstart](https://docs.camb.ai/sdk-guides/java-sdk-quickstart.md)
- [PHP SDK Quickstart](https://docs.camb.ai/sdk-guides/php-sdk-quickstart.md)
- [Python SDK Quickstart](https://docs.camb.ai/sdk-guides/python-sdk.md): Get started with the Camb.ai Python SDK in minutes
- [Rust SDK Quickstart](https://docs.camb.ai/sdk-guides/rust-sdk-quickstart.md)
- [TypeScript SDK Quickstart](https://docs.camb.ai/sdk-guides/typescript-sdk.md): Get started with the Camb.ai TypeScript SDK in minutes
- [TTS via RAW API Calls](https://docs.camb.ai/tutorials/direct-api.md): Use the Camb.ai TTS API directly for maximum control and flexibility
- [Emotional Voice Control](https://docs.camb.ai/tutorials/emotional-voice-control.md): Create emotionally nuanced speech with director-level control over tone, pacing, and character voice
- [Text to Sound Effects](https://docs.camb.ai/tutorials/text-to-sound.md): Generate sound effects and music from text prompts
- [Translated TTS](https://docs.camb.ai/tutorials/translated-tts.md): Automatically translate text and generate speech in the target language
- [TTS with Accents](https://docs.camb.ai/tutorials/tts-with-accents.md): Generate natural speech in 140+ language accents
- [Text to Speech](https://docs.camb.ai/tutorials/tts-with-sdk.md): Generate speech from text using the Python or TypeScript SDK
- [Voice Cloning](https://docs.camb.ai/tutorials/voice-cloning.md): Clone a voice from reference audio and generate speech with it

## OpenAPI Specs

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

## AsyncAPI Specs

- [asyncapi](https://docs.camb.ai/api-reference/websockets/asyncapi.json)