FlowSpeech Dart SDK #

flowspeech is a small Dart client for the FlowSpeech text-to-speech API. It helps Dart and Flutter apps generate human-like speech audio from text, check account quota, and work with the API response metadata.

FlowSpeech supports context-aware text-to-speech generation, emotion and pause control, voice selection, and multi-speaker requests.

Installation #

dependencies:
  flowspeech: ^0.1.0

Then run:

dart pub get

Authentication #

Create a FlowSpeech API key in your FlowSpeech account and pass it to the client:

final client = FlowSpeechClient(apiKey: 'fs_your_api_key');

For server-side Dart apps, you can also read the key from an environment variable:

final client = FlowSpeechClient.fromEnvironment();

Do not ship API keys inside public mobile, desktop, or web clients. For Flutter apps, generate audio through your own backend when the key must stay private.

Generate speech #

import 'dart:io';

import 'package:flowspeech/flowspeech.dart';

Future<void> main() async {
  final client = FlowSpeechClient.fromEnvironment();

  final result = await client.generateSpeech(
    text: 'Welcome to FlowSpeech. This audio was generated from Dart.',
    voiceName: 'Kore',
  );

  await File('flowspeech-output.wav').writeAsBytes(result.audioBytes);
  print(result.mimeType);
  print(result.quota?.remaining);

  client.close();
}

Multi-speaker requests #

final result = await client.generateSpeech(
  text: 'Speaker A: We can make this sound natural.\nSpeaker B: Great, use two voices.',
  speakers: const [
    FlowSpeechSpeaker(speaker: 'Speaker A', voiceName: 'Kore'),
    FlowSpeechSpeaker(speaker: 'Speaker B', voiceName: 'Puck'),
  ],
);

Check quota #

final quota = await client.checkQuota();
print('${quota.remaining} characters remaining');

API surface #

This package uses the public FlowSpeech API:

• GET /api/ai/text-to-speech/quota
• POST /api/ai/text-to-speech

Responses include base64 audio and metadata such as MIME type, sample rate, channel count, bit depth, and quota.

License #

MIT