Paste your text, pick a voice and listen right away.
Free text to speech: paste up to 3,000 characters, pick a voice and listen in your browser. The voices load in a moment.
Free text to speech: paste up to 3,000 characters, pick a voice and listen in your browser. The voices load in a moment.
VoiceHue is a free online text-to-speech (TTS) tool that reads your text aloud with natural-sounding AI voices. Paste your text, pick a voice and listen in your browser. You do not need an account or to install anything.
Without an account you can convert 10,000 characters a day; when you are signed in, 30,000 characters a day. For a longer script, split it at a paragraph break and convert the parts one after another. Developers can get an API key with a free plan once signed in.
New to text to speech?
Read the overviewFollows the OpenAI speech format, so you only change the base URL. A free plan includes 10,000 characters a month; paid credit packs come later.
from openai import OpenAI
client = OpenAI(base_url="https://voicehue.com/v1", api_key="YOUR_API_KEY")
client.audio.speech.create(
model="voicehue-tts", voice="VOICE_ID",
input="Hello from VoiceHue.",
).write_to_file("hello.mp3")Yes, it is free and you do not need an account. Open the page, paste your text, pick a voice and press play; there is no sign-up and no credit card.
3,000 characters per conversion. For a longer script, split it into parts of up to 3,000 characters and convert them one after another.
Speech works for English, Chinese (Mandarin), Japanese, Spanish, French and Portuguese. VoiceHue's cloud voices cover English, Chinese, Spanish, French, Japanese and Korean and download as MP3. English, Spanish, Portuguese and French can also be generated on your device; other languages play with the voices your browser provides. The site itself is available in English, Chinese, Spanish and Portuguese (Brazil).
No. VoiceHue runs in your browser on desktop and mobile, with nothing to install. The first time you generate speech with an on-device voice, your browser downloads that voice once, so the first run takes a little longer.