Answers about using ttsMP3, downloading MP3 files, commercial use, Regular Voices, AI Voices, API access, invoices and common troubleshooting issues.
ttsMP3 is an online text-to-speech tool that converts written text into spoken audio. After conversion, you can download the generated speech as an MP3 file and use it in your own projects.
Yes. You can convert up to 3,000 characters a day (about 375 words) with the regular voices and download the result as an MP3 file, without an account or sign-up. The AI voices have their own free limit of 1,000 characters a day. If you need more, there are 24-hour passes, monthly plans and yearly plans.
No. The free converter works without an account, sign-up or app: enter your text, choose a voice and download the MP3. An account is only created when you buy a pass or plan, so you can sign in and use your larger quota.
Choose a voice, enter your text, and start the conversion. Once the speech has been generated, you can listen to it and download the finished MP3 file.
Free use allows 3,000 characters a day with the regular voices and 1,000 characters a day with the AI voices. The free limit resets every day. With a pass or plan you can convert much longer texts in one go; long texts are processed in the background and you get the finished MP3 when it is ready.
Yes. After the conversion the audio plays directly in your browser, so you can use ttsMP3 to read a text out loud or to check the pronunciation of a word. Downloading the MP3 file is optional.
Yes. ttsMP3 runs in any modern web browser on phones, tablets and computers. No app or plugin is needed.
All files are mono MP3 files in speech quality: the regular voices at 22 to 24 kHz and 48 kbit/s, the AI voices at 24 kHz and 128 kbit/s. MP3 plays on practically every device and in every video or presentation program.
Yes, for a limited time. The generated MP3 files of both the regular and the AI voices are kept on our servers (long texts with the regular voices in Amazon S3) so the same request can be answered again, and anyone who has the link to a file can open it. Files that have not been used for three months are usually deleted. The converted text is deleted after 12 months, the IP address after 90 days. Please do not convert confidential or sensitive information. Details are in our privacy policy at https://ttsmp3.com/privacypolicy.
Yes. You may use the MP3 files created with ttsMP3 in commercial and non-commercial projects, including YouTube videos, presentations, websites, apps and e-learning content. This applies to both free and paid usage. A backlink or mention is appreciated, but not required.
No. You do not have to credit ttsMP3 when using generated MP3 files. We are always happy about mentions or backlinks, but they are not mandatory.
Regular Voices are powered by Amazon Polly and support SSML features such as breaks, emphasis, speed, pitch and whispering. AI Voices are generated by modern AI speech models (OpenAI and Google Gemini) and sound more natural, with expressive intonation. You can add a voice instruction such as "calm and warm", "excited sports commentator" or "slow, for language learners" to set style, tone, emotion and accent. The AI voices also detect the language of your text automatically. You can listen to samples of every AI voice at https://ttsmp3.com/ai.
ttsMP3 supports many languages and speakers. The regular voice converter offers voices in more than 40 languages and accents, each with its own language page. The AI voice converter supports a separate set of automatically detected languages. The available voices can change when new voices are added by the underlying voice providers.
Regular Voices support several SSML options, including pauses, emphasis, speed, pitch and whisper effects. AI Voices support pauses and voice instructions, but pitch and tone are not adjusted in the same direct way as with Regular Voices.
No. You can download the generated MP3 files, but the voice models themselves are not downloadable and cannot be used offline. Regular Voices are provided through Amazon Polly, and AI Voices are provided through OpenAI and Google Gemini text-to-speech.
We understand that users often need more languages, accents and speaker options. However, the available voices depend on the underlying voice providers. We collect feedback and pass demand for new voices along where possible, but we do not directly decide which voices are released next.
Yes. API access is included with the yearly plan for regular voices. After your purchase, you can create your API key yourself in Manage My Account › Account Information. The API documentation is available at https://ttsmp3.com/apidoc.
The ttsMP3 API lets you send text, choose a speaker and receive a generated MP3 file URL in the response. It can be used for apps, websites and automated text-to-speech workflows.
Your login information is displayed directly after purchase and is also sent by e-mail. Please check your inbox and your junk or spam folder. If you still cannot find the e-mail, contact us and we will help you. You will not lose account validity because of a missing login e-mail.
Yes. Please contact us by e-mail and include the information required for your invoice. We usually need your full billing address. If you are located in the European Union and purchased for a company, please also include your VAT ID.
A conversion can fail if the voice service is temporarily unreachable, if your account quota would be exceeded, or if the text contains invalid formatting. Special characters such as unescaped < or > symbols can also cause problems when they are interpreted as broken SSML tags.
You can contact us by e-mail using the address shown on this page. Please include the e-mail address used for your purchase and a short description of the issue so we can help faster.
Still need help?
Send us an e-mail and include your account e-mail address, the voice you used and a short description of the problem.