FlowSpeech
FlowSpeech integrates with Drupal AI to convert text into speech using the FlowSpeech API. It offers a variety of voices that can be used within Drupal AI-powered workflows, ultimately delivering audio as standard WAV files.
FlowSpeech provides a text-to-speech provider plugin for Drupal AI. It sends text to the FlowSpeech API and returns standard WAV audio for AI Automator and other modules built on Drupal AI.
Features
- Text-to-speech support through the Drupal AI provider system.
- 30 voices for narration, education, marketing, and character audio.
- API credentials stored through the Key module.
- Raw PCM responses converted to playable WAV files.
- Support for Drupal 10.2 and Drupal 11.
Post-Installation
- Create a key in the Key module containing your FlowSpeech API key.
- Open Configuration > AI > Providers > FlowSpeech.
- Select the key and save the provider settings.
- Select FlowSpeech as the text-to-speech provider in a compatible Drupal AI workflow.
Additional Requirements
- Drupal AI 1.0.5 or later.
- Key 1.18 or later.
- A FlowSpeech account and API key.
Similar projects
Other Drupal AI provider integrations expose text-to-speech services. This module is specifically for the FlowSpeech API and includes PCM-to-WAV conversion so generated audio can be consumed as a standard WAV file.
Supporting this Module
Use this project's issue queue for bug reports and feature requests.
Community Documentation
See the project README for installation, configuration, usage, and development instructions.
Depends on
Dependencies of the latest stable release
Required by
Tracked projects that depend on this one
No tracked projects depend on this one yet.
Activity
Releases
| Version | Type | Core | Notes | Release date | |
|---|---|---|---|---|---|
| 1.0.0 | Stable | 10–11 | Initial FlowSpeech text-to-speech provider for Drupal AI. | Jul 30, 2026 |