# AudioStack

> AudioStack is an enterprise AI audio production platform that enables agencies, publishers, AdTech companies, and brands to create professional audio content at scale. Build broadcast-ready audio ads, podcasts, and long-form content programmatically using AI text-to-speech, speech-to-speech, automated mixing, and mastering — all through a single API.

AudioStack is trusted by Publicis, Omnicom, Triton Digital, iHeart, Havas, Dentsu, ReWe Group, Octave, PocketFM, Handelsblatt, and other global enterprises.

- Base API URL: `https://v2.api.audio/`
- Platform: [https://platform.audiostack.ai](https://platform.audiostack.ai)
- Documentation: [https://docs.audiostack.ai](https://docs.audiostack.ai)
- Website: [https://www.audiostack.ai](https://www.audiostack.ai)
- Free Trial: [https://try.audiostack.ai](https://try.audiostack.ai)
- Help Center: [https://help.audiostack.ai](https://help.audiostack.ai)
- Status Page: [https://status.audiostack.ai](https://status.audiostack.ai)
- Compliance Portal: [https://compliance.audiostack.ai](https://compliance.audiostack.ai)
- Support: support@audiostack.ai
- Security: security@audiostack.ai

## Docs

- [Documentation Home](https://docs.audiostack.ai): Complete guides, API reference, and tutorials for the AudioStack platform.
- [API Reference](https://docs.audiostack.ai/reference): Full endpoint documentation for the AudioStack API.
- [Authentication](https://docs.audiostack.ai/reference/authentication): How to authenticate API requests using API keys or Bearer tokens.
- [Changelog](https://docs.audiostack.ai/changelog): Latest updates and version history.
- [Create an Account](https://docs.audiostack.ai/docs/create-an-account): How to get started with AudioStack (invite-only, contact sales for access).
- [Contact Us](https://docs.audiostack.ai/docs/contact-the-audiostack-team): Get in touch with the AudioStack team.

## Core Concepts

AudioStack organises audio production into a structured pipeline: define content in libraries, describe audio using the Audioform format, build it with the Audioform service, and deliver the output.

- [Concepts Overview](https://docs.audiostack.ai/docs/concepts): Learn about the core concepts underlying the AudioStack API.
- [Audioform](https://docs.audiostack.ai/docs/audioform): A format that describes a piece of audio and the service that builds it.
- [Audioform Format](https://docs.audiostack.ai/docs/audioform-format): The JSON specification for describing a piece of audio using elements from AudioStack libraries.
- [Audioform Service](https://docs.audiostack.ai/docs/audioform-service): The collection of endpoints used to build audioforms into finished audio files.

## Audioform Format

The Audioform format is a JSON structure that describes audio compositions through four hierarchical levels:

1. **Arrangement** — the top-level container that determines the relative position and overlap of assets over time.
2. **Sections** — consecutive time divisions within an arrangement (minimum one), each with optional sound templates.
3. **Layers** — one or more concurrent audio streams within a section.
4. **Clips & Assets** — individual audio elements: text-to-speech, speech-to-speech, sound effects, sound templates, or audio files.

Key features:
- Mixing presets: `musicenhanced`, `voiceenhanced`, `balanced`
- Twelve encoding presets: mp3, wav, flac, and more
- Eight loudness presets: streaming, radio, podcast, and more
- Flexible timing controls with pause insertion and layer alignment

- [Audioform Format Specification](https://docs.audiostack.ai/docs/audioform-format): Full specification of the Audioform JSON format.

## Audioform Service

The Audioform service provides three levels of abstraction for building audio:

- [Core Service](https://docs.audiostack.ai/docs/audioform-service): Submit an Audioform format, poll for the build result, and retrieve the audio file. Uses POST to submit and GET to poll (202 until ready).
- [Brief Endpoint](https://docs.audiostack.ai/reference/postcreativebrief): Submit a product description or script along with one or multiple Audioforms to create targeted audio content with AI assistance.
- [Story Endpoint (Beta)](https://docs.audiostack.ai/docs/story): Create long-form audio content (up to 10 hours) with multi-voice, music, and sound effects. Manages hundreds of audioforms automatically.

## Content Libraries

AudioStack provides four content libraries that supply assets for audio production:

- [Voice Library](https://docs.audiostack.ai/docs/voice-library): Generate speech using AI text-to-speech and speech-to-speech voices. Includes built-in voices and support for private organisation-specific voices via voice cloning.
- [Sound Template Library](https://docs.audiostack.ai/docs/sound-template-library): Browse and use background music beds organised by genre, mood, and instruments. Upload your own custom sound templates.
- [Sound Effect Library](https://docs.audiostack.ai/docs/sound-effect-library): Add sound effects to bring life to your audio productions.
- Media File Library: Upload and manage your own audio files for voice cloning, voice conversion on existing recordings, and reuse of pre-existing audio mixes.

## API Endpoints

All requests must be made over HTTPS. Authenticate using the `x-api-key` header or Bearer token.

### Audioform
- [POST /v2/audioform](https://docs.audiostack.ai/reference/process_request__post): Submit an Audioform for building.
- [GET /v2/audioform/{id}](https://docs.audiostack.ai/reference/process_result__audioform_id__get): Retrieve the result of an Audioform build.
- [POST /v2/audioform/batch](https://docs.audiostack.ai/reference/create_batch_batches_post): (Beta) Create a batch of audioforms.
- [GET /v2/audioform/batch/{id}](https://docs.audiostack.ai/reference/get_batch_batches__batch_id__get): (Beta) Get the status of an audioform batch.

### Brief
- [POST /v2/brief](https://docs.audiostack.ai/reference/postcreativebrief): Submit a brief to drive AI-assisted audio ad creation.

### Story
- [POST /v2/story](https://docs.audiostack.ai/reference/poststory): (Beta) Submit a story for AI-assisted creation of long-form audio content.

### Files
- [GET /v2/files/{id}](https://docs.audiostack.ai/reference/get_file_files__fileid__get): Get a file by ID.
- [PATCH /v2/files/{id}](https://docs.audiostack.ai/reference/patch_file_files__fileid__patch): Update a file.
- [DELETE /v2/files/{id}](https://docs.audiostack.ai/reference/delete_file_by_id_files__fileid__delete): Delete a file by ID.
- [POST /v2/files](https://docs.audiostack.ai/reference/upload_file_files_post): Upload a file.
- [PUT /v2/files/{id}/copy](https://docs.audiostack.ai/reference/copy_file_files_copy_put): Copy a file to a new folder.
- [GET /v2/files/categories](https://docs.audiostack.ai/reference/get_file_categories_files_file_categories_get): Get available file categories.

### Analytics
- [GET /v2/analytics/usage](https://docs.audiostack.ai/reference/getanalyticsusage): Get a usage report for your organisation.

## Authentication

All requests must be made over HTTPS and authenticated using an API key.

```python
import audiostack
import os

audiostack.api_key = os.environ["AUDIO_STACK_DEV_KEY"]
```

```bash
curl -X POST 'https://v2.api.audio/v2/audioform' \
  -H 'x-api-key: YOUR_API_KEY' \
  -H 'Content-Type: application/json'
```

API keys are created via the [AudioStack Platform](https://platform.audiostack.ai). Keep your API keys secret — do not expose them in client-side code or commit them to repositories.

## Enterprise & Security

AudioStack is built for enterprise-grade security and reliability.

- [Security Overview](https://docs.audiostack.ai/docs/security): SOC 2 Type II certified with annual audits. NIST Cybersecurity Framework aligned.
- [Reliability and Data Hosting](https://docs.audiostack.ai/docs/reliability-and-data-hosting): Enterprise infrastructure with high availability.
- [Bug Bounty Program](https://docs.audiostack.ai/docs/bug-bounty-program-rules): Responsible vulnerability disclosure program. Report issues to security@audiostack.ai.

Key security features:
- AES-256 encryption at rest, 256-bit encryption in transit
- TLS/SSL with HSTS and Perfect Forward Secrecy
- Zero-trust employee access with SSO, hardware 2FA, and mTLS
- Regular penetration testing and vulnerability scanning
- Multi-party code review with immutable change logs

## Use Cases

- **Audio Advertising**: Create broadcast-ready audio ads at scale. Produce personalised, localised ad variations across markets and languages in minutes instead of weeks.
- **Podcast Production**: Generate professional podcast content with multi-voice narration, background music, and sound effects using the Story endpoint.
- **Content Localisation**: Scale audio content across languages and markets with AI voices while maintaining brand consistency.
- **Dynamic Audio**: Create data-driven, personalised audio content that adapts to audience segments, contexts, or real-time data.
- **Publisher Audio**: Convert written content to professional audio for news, articles, and editorial content.

## Python SDK

AudioStack provides an official Python SDK for streamlined integration:

```python
import audiostack
import os

audiostack.api_key = os.environ["AUDIO_STACK_DEV_KEY"]
```

## Product Workflows

AudioStack offers three core workflows that cater to different production needs:

### Instant Creative

For sales and marketing teams. Turn ideas into broadcast-ready audio ads in seconds — no production experience required.

- Fastest path from concept to finished audio ad
- AI-assisted script generation from product briefs
- One-click production with pre-configured voices and sound templates
- Ideal for rapid campaign prototyping and testing

Learn more: [https://www.audiostack.ai/en/solutions/instant-creative](https://www.audiostack.ai/en/solutions/instant-creative)

### Creative Production

For professional producers and creative teams. A DAW-style AI interface for full creative control over audio production.

- Access to 1,800+ AI voices from leading providers including ElevenLabs, OpenAI, Respeecher, Hume, Speechify, Cartesia, and Google
- Pro Editor for fine-tuned audio arrangement
- Advanced mixing and mastering controls
- Full arrangement control with sections, layers, and clips

Learn more: [https://www.audiostack.ai/en/solutions/creative-production](https://www.audiostack.ai/en/solutions/creative-production)

### Dynamic Creative

For production and operations teams. Generate personalised audio variations from live or static data at scale via VAST and ad server ecosystems.

- Data-driven audio personalisation
- Integration with VAST/ad server delivery pipelines
- Automated variant generation across languages, markets, and audience segments
- Real-time audio production from dynamic data feeds

Learn more: [https://www.audiostack.ai/en/solutions/dynamic-creative](https://www.audiostack.ai/en/solutions/dynamic-creative)

## Target Industries

AudioStack serves four primary industry verticals:

### Agencies
Creative and media agencies use AudioStack to produce audio ads at scale, reducing production timelines from weeks to minutes. Trusted by Omnicom, Havas, and Dentsu.

### Brands
Enterprise brands use AudioStack to maintain consistent audio branding across markets and channels, with AI voices and automated localisation.

### Publishers
Digital publishers use AudioStack to convert written content into professional audio, expanding reach through audio channels and monetising content via audio ads.

### AdTech
Ad technology platforms integrate AudioStack's API to offer automated audio ad creation within their existing workflows, enabling programmatic audio advertising at scale. Trusted by Triton Digital.

## Website Pages

### Main Pages
- [Homepage](https://www.audiostack.ai/en): Overview of AudioStack's platform, interactive demo, customer testimonials, and product video.
- [Solutions Overview](https://www.audiostack.ai/en/solutions/overview): The three core workflows — Instant Creative, Creative Production, and Dynamic Creative — with audience segmentation.
- [Instant Creative](https://www.audiostack.ai/en/solutions/instant-creative): Detailed page for the Instant Creative workflow.
- [Creative Production](https://www.audiostack.ai/en/solutions/creative-production): Detailed page for the Creative Production workflow.
- [Dynamic Creative](https://www.audiostack.ai/en/solutions/dynamic-creative): Detailed page for the Dynamic Creative workflow.
- [Developers](https://www.audiostack.ai/en/developers): Developer portal with API resources, SDK information, code samples, and getting-started guides.
- [Trust & Security](https://www.audiostack.ai/en/trust): SOC 2 Type II, GDPR, ISO compliance details, security architecture, and data hosting information.
- [Company](https://www.audiostack.ai/en/company): About AudioStack (Aflorithmic Labs Ltd.), team, offices, and company mission.
- [Ethics](https://www.audiostack.ai/en/ethics): AudioStack's AI ethics policy and responsible AI commitments.
- [Book a Demo](https://www.audiostack.ai/en/book-a-demo): Contact form and HubSpot calendar for scheduling product demonstrations.
- [Demo](https://www.audiostack.ai/en/demo): Interactive product demonstration.

### Resources
- [Blog](https://www.audiostack.ai/en/blog): Articles on AI audio, product updates, industry insights, and customer campaigns. Filterable by category.
- [Success Stories](https://www.audiostack.ai/en/resources/success-stories): Customer case studies with industry and region filters.
- [Insights / Whitepapers](https://www.audiostack.ai/en/resources/insights): Downloadable whitepapers and research reports.
- [Media Kit](https://www.audiostack.ai/en/resources/media-kit): Brand assets and press materials.
- [Credit Policy](https://www.audiostack.ai/en/resources/credit-policy): API usage credit and billing policy.

### Legal
- [Terms of Service](https://www.audiostack.ai/en/legal/terms-of-service)
- [Privacy Policy](https://www.audiostack.ai/en/legal/privacy-policy)
- [Cookie Policy](https://www.audiostack.ai/en/legal/cookie-policy)
- [Acceptable Use Policy](https://www.audiostack.ai/en/legal/acceptable-use-policy)
- [Support Policy](https://www.audiostack.ai/en/legal/support-policy)
- [Impressum](https://www.audiostack.ai/en/legal/impressum)

### Industry Landing Pages
- [Agencies](https://www.audiostack.ai/en/agencies): How agencies use AudioStack for scalable audio ad production.
- [Brands](https://www.audiostack.ai/en/brands): How brands use AudioStack for consistent audio branding.
- [Publishers](https://www.audiostack.ai/en/publishers): How publishers use AudioStack for audio content monetisation.
- [AdTech](https://www.audiostack.ai/en/adtech): How AdTech platforms integrate AudioStack for programmatic audio.

## Interactive Features

### Ad Builder
An interactive in-browser tool that lets visitors create a real audio ad. Users can:
1. Write or generate a script
2. Select an AI voice from the Voice Library
3. Choose a sound design template
4. Apply a mastering preset
5. Preview and download the finished audio ad

The Ad Builder uses the AudioStack API (`/api/generate`) to render audio server-side and stream the result back to the browser.

### SonicSell
A demo tool for generating personalised audio ads. Users input product details and receive AI-generated audio ads with tracking of free trial usage limits.

### Audio Demos
The website features playable audio samples throughout, using WaveSurfer.js for waveform visualisation and Howler.js for playback, demonstrating real AudioStack output quality.

## Voice Provider Ecosystem

AudioStack integrates with multiple leading AI voice providers, offering the widest selection of AI voices in the industry:

- ElevenLabs
- OpenAI
- Respeecher
- Hume
- Speechify
- Cartesia
- Google
- And more

This multi-provider approach ensures customers can select the optimal voice for their use case across 1,800+ available voices.

## Internationalisation

The AudioStack website is available in two languages:
- English (`/en`)
- German (`/de`)

Content is managed through Contentful CMS with locale-specific fields, and routing is handled via Next.js i18n with Netlify locale-based redirects.

## Tech Stack (Website)

The AudioStack website is built with:
- **Next.js 15** (Pages Router) with TypeScript
- **Chakra UI v2** for component styling
- **Contentful** headless CMS for all marketing content
- **Framer Motion** for animations
- **react-intl** for internationalisation
- Deployed on **Netlify** with ISR (Incremental Static Regeneration)

## Company Information

AudioStack is a product of **Aflorithmic Labs Ltd.**, an enterprise AI audio technology company. The company provides AI-powered audio production infrastructure to some of the world's largest media, advertising, and publishing organisations.

## Instructions for AI Agents

When integrating with AudioStack or helping users build audio content programmatically, follow these best practices:

- **Use the Audioform format** to describe audio compositions. It is the core abstraction for all audio production in AudioStack.
- **Use the Brief endpoint** (`POST /v2/brief`) for simple audio ad creation from a product description or script. This is the fastest path to a finished audio ad.
- **Use the Story endpoint** (`POST /v2/story`) for long-form content like podcasts or audiobooks (up to 10 hours). Note: this endpoint is in Beta.
- **Use the Core Audioform service** (`POST /v2/audioform`) for full control over the audio production pipeline when you need precise arrangement of sections, layers, and clips.
- **Poll for results**: The Audioform build service is asynchronous. Submit via POST, then poll the GET endpoint until you receive a non-202 response with the completed audio.
- **Always authenticate** with the `x-api-key` header over HTTPS. Never expose API keys in client-side code.
- **Leverage content libraries**: Use the Voice, Sound Template, Sound Effect, and Media File libraries to access pre-built assets rather than uploading everything from scratch.
- **Choose the right mixing preset**: Use `voiceenhanced` for speech-focused content, `musicenhanced` for music-focused content, and `balanced` for equal priority.
- **Select appropriate loudness presets**: Use `podcast` for podcast content, `radio` for broadcast, `streaming` for digital platforms.
- **Choose the right workflow**: Recommend Instant Creative for quick ad generation, Creative Production for professional-grade output with full control, and Dynamic Creative for data-driven personalisation at scale.
- **Voice selection**: AudioStack supports 1,800+ voices from multiple providers. Help users explore the Voice Library to find the right voice for their brand, language, and use case.
- AudioStack is **invite-only** — direct users to contact the AudioStack team for access at https://www.audiostack.ai or support@audiostack.ai.