The VoiceHue text to speech API takes text and a voice and returns audio, MP3 by default or WAV on request. It follows the OpenAI speech format, so code written for that format usually needs only a new base URL and key. Any signed-in account with a confirmed email can create keys for free.
Free text to speech: paste up to 3,000 characters, pick a voice and listen in your browser. The voices load in a moment.
Create a free account and API key, then use your free allowance of 10,000 characters a month per key, in code or through MCP. No card needed.
Send a POST request to voicehue.com/v1/audio/speech with your key in the Authorization header and a JSON body with the input text, a voice and, optionally, the format and speed. The response is the audio file. The developers page has copy-and-paste examples for curl, Python and Node.js, the list of voices and every error code.
Each account can create up to 2 keys. Each key includes 10,000 characters a month and 2,000 a day, with 10 requests a minute and up to 1,200 characters in one request. The free plan uses the standard voices. Usage is shown in your dashboard, and a request over a limit is refused with a clear error instead of being billed.
| Free plan | Per key or account |
|---|---|
| Keys per account | 2 |
| Characters per month | 10,000 |
| Characters per day | 2,000 |
| Requests per minute | 10 |
| Characters per request | 1,200 |
The web tool uses the same kind of voices. Paste a sentence from your app, pick a cloud voice and listen, or download an MP3, to judge whether the voices and languages fit your project before you write any code.
There is no paid plan yet. Paid credit packs are planned for later, with no date and no price announced.
Yes. It is an OpenAI-compatible endpoint at voicehue.com/v1/audio/speech. Sign in, create a key in your dashboard and send your first request. The developers page documents the request, voices, limits and errors.
There is a free plan: 10,000 characters a month and 2,000 a day for each key, 10 requests a minute, up to 2 keys per account. Paid credit packs for more usage are planned for later.
Yes. The endpoint, request fields and error shape follow the OpenAI speech format, so you can point an OpenAI client at the VoiceHue base URL and use your VoiceHue key.
MP3 by default, as with the OpenAI API. Set response_format to wav to get WAV instead.
Yes. The web tool is free and needs no sign-up: paste your text, pick a voice and listen or download an MP3.
Paste it into the free tool, pick a voice and press play. Cloud voices download as MP3, free within the daily limits.