What Is Cloud TTS in SoundWorks?
SoundWorks integrates six cloud text-to-speech providers into a single desktop interface. Instead of switching between web dashboards or writing API scripts, you configure your personal API keys once and access all providers through the same workflow.
Supported engines: OpenAI TTS, ElevenLabs, Anthropic Claude, AWS Polly, IBM Watson, and Yandex SpeechKit.
Each engine has different strengths — natural conversational delivery, multilingual coverage, ultra-low latency, or specialized voice cloning. SoundWorks lets you compare them side by side and pick the best voice for each project.
Why Use Cloud TTS?
Access premium voices without vendor lock-in. Switch between OpenAI, ElevenLabs, AWS Polly, and others without changing your workflow. Compare results across providers to find the best voice for your content.
Use your own API keys. SoundWorks never routes traffic through third-party servers. Your API keys connect directly to the provider. You pay provider rates with no markup or subscription.
Batch processing built in. Generate speech for entire scripts, not just single sentences. SoundWorks handles text chunking, queue management, and file assembly automatically.
SSML support. For engines that support it, add precise pauses, emphasis, and pronunciation control using SSML markup directly in your text.
Supported Engines
OpenAI TTS
OpenAI’s text-to-speech models produce natural, conversational speech. Multiple voice presets are available, each with distinct personality and tone. Supports long-form content generation.
ElevenLabs
ElevenLabs specializes in ultra-realistic voice synthesis with advanced voice cloning capabilities. SoundWorks provides a dedicated interface with stability and similarity controls, voice library management, and usage history tracking. Create custom voices from reference audio or choose from the ElevenLabs voice marketplace.
AWS Polly
Amazon Polly offers dozens of voices across 30+ languages. Neural voices deliver broadcast-quality results. Full SSML support for fine-grained control over pronunciation, pauses, and speech rate.
IBM Watson
IBM Watson Text to Speech provides enterprise-grade synthesis with precise language model control. Strong multilingual coverage and consistent quality for professional narration projects.
Yandex SpeechKit
Yandex SpeechKit excels at Russian and CIS-region languages with natural intonation. Also supports English and other languages. Competitive pricing for high-volume projects.
Anthropic Claude
Use Claude for AI-assisted voice script generation and refinement before synthesis. Integrated into the TTS workflow for content creation and polishing.
How It Works
Step 1: Add API keys. Open the API Keys Manager and enter your keys for one or more providers. Keys are stored locally in an encrypted vault.
Step 2: Select an engine. Choose the TTS engine for your project. Browse available voices and preview samples.
Step 3: Enter or import text. Type your text, paste a script, or import from a file. For long content, SoundWorks automatically splits text into chunks that respect sentence boundaries.
Step 4: Generate. Start synthesis. SoundWorks processes each chunk, handles API rate limits, and assembles the final audio file. Output is saved in your chosen format.
Offline Fallback
If your internet connection drops or you want to avoid cloud costs entirely, SoundWorks includes three fully offline TTS engines — Silero, IndexTTS2, and Qwen3 — that require no API keys and no internet connection. You can switch between cloud and local engines at any time.
Frequently Asked Questions
Do I need accounts with all six providers? No. You only need API keys for the providers you want to use. Even a single provider is enough to get started.
Does SoundWorks charge for cloud TTS usage? No. You pay only the provider’s standard API rates. SoundWorks adds no markup, subscription, or per-character fee.
Can I use cloud TTS for commercial projects? That depends on each provider’s terms of service. Check the licensing terms for your specific provider and voice selection.
What audio formats are generated? Output format depends on the provider. SoundWorks can convert the result to MP3, WAV, AAC, or other formats automatically using the built-in audio converter.