flowspeech-cli

flowspeech-cli is a small command-line client for FlowSpeech, a context-aware text to speech tool for generating human-like audio with voice, emotion, and pause control.

The CLI calls FlowSpeech's public text-to-speech endpoint and writes the returned audio to a local file. It does not contain provider API keys and does not ask for Gemini, FAL, Azure, or ElevenLabs credentials.

Install

pip install flowspeech-cli

For local development from this repository:

python -m pip install -e packages/flowspeech-cli

Usage

Generate speech from inline text:

flowspeech synthesize "FlowSpeech turns scripts into natural audio." --voice Kore --out speech.wav

Generate speech from a text file:

flowspeech synthesize --file script.txt --out narration.wav

Check CLI configuration:

flowspeech doctor

Use a different FlowSpeech-compatible endpoint:

flowspeech synthesize "Hello" --api-url https://flowspeech.io/api/ai/text-to-speech --out hello.wav

Privacy And Credentials

• No third-party provider API keys are bundled or requested.
• No local authentication token is saved by default.
• Input text is sent to the configured FlowSpeech API endpoint for speech generation.
• Output audio is written only to the path you pass with --out.

Status

This is an early CLI for FlowSpeech. The default command supports single-speaker generation. Multi-speaker helpers and authenticated account workflows can be added later without changing the no-provider-key boundary.

Releasing

See RELEASE.md for TestPyPI and PyPI preparation. Publishing requires a PyPI API token handled outside the repository; do not commit credentials or generated distributions.