Resona

Resona is an online voice cloning and text-to-speech platform for creators, publishers, and developers who want high-quality AI voices without a monthly subscription. It brings the full voice workflow into one place—text-to-speech, voice cloning, a large ready-to-use voice library, real-time streaming, and speech-to-text.

With voice cloning, you can upload a sample to create a reusable voice model. Cloning is built for quick iteration: provide a short voice sample (typically 10–30 seconds), generate audio in the console, and download the results. Resona also supports direct text-to-speech in 80+ languages, including multiple TTS model options for different use cases, plus emotion tags and streaming support.

Need real-time behavior for voice agents or dialogue? Resona offers WebSocket streaming with low streaming latency (~90ms). You can also use its 200,000+ community voice library for zero-shot, ready-to-call voices, and transcribe audio with speech-to-text billed per audio hour.

Resona is pay-as-you-go with no fixed monthly fee. You top up credits, and every deduction is itemized in your dashboard. TTS is billed per UTF-8 byte (1,500 credits per 1M bytes). Voice cloning costs 100 credits for cloning, transcription is billed at 0.15 credits per second of audio, and credits never expire. Every clone uses your credit balance.

How do I clone a voice with Resona?

Upload a voice sample (typically 10–30 seconds) to generate a reusable voice model, then use it in the console to generate and download audio. Cloning is charged in credits.

Is there a monthly subscription for Resona?

No—Resona uses pay-as-you-go pricing with no monthly fee. You top up credits and pay only for what you use.

How is text-to-speech priced?

TTS is billed per UTF-8 byte (1,500 credits per 1M bytes). Your dashboard itemizes each deduction.

What languages and voices does Resona support?

Resona supports 80+ languages for text-to-speech and includes a library of 200,000+ community voices you can call without cloning.

Can Resona stream audio in real time?

Yes. It supports WebSocket streaming with streaming latency around ~90ms, which is suitable for voice agents and dialogue.

How is speech-to-text priced?

Speech-to-text is billed per second of audio at 0.15 credits per second, with support for multi-speaker and emotion tags.