Ranked #1 in Speech Arena
Text to speech MP3, free to download
Join the teams making the switch to Cartesia
How to convert text to MP3
Paste your text
Type or paste up to 500 characters into the box at the top of this page.
Choose a language and voice
Pick from 40+ languages, then press play to hear the voice read your script before you download it.
Download the MP3
Select Create MP3, then Download MP3. You get a 44.1 kHz, 128 kbps file that opens in any audio player or editor.
Put your MP3 to work
Phone greetings and hold messages
Voicemail greetings and hold messages as MP3s you upload to your phone system. When your hours change, the new MP3 is one script edit away.
Audio for apps and courses
Spoken instructions and lesson audio for your app or course, as MP3 files you add like any other audio, with no microphone or recording session.
A voice for your agent
Every voice on this page also works through the API in live voice agents, so the voice you hear on your script is the one your callers hear.
Generate an MP3 through the API
For hundreds of files, or scripts longer than 500 characters, the API returns the same MP3s straight to your backend.
Configure your request
In the same request as your transcript, voice and model, set the output container to mp3 with a sample rate and bit rate. Send the request from your backend so your API key stays private.
Save the audio response
The response body is the MP3 itself. Write the bytes to a file ending in .mp3 and it's ready to play.
- Format
- MP3
- Sample rate
- 44.1 kHz
- Bit rate
- 128 kbps
Explore more voice tools
Text to MP3 FAQs
How do I save text to speech as an MP3 for free?
Paste up to 500 characters into the tool at the top of this page, choose a language and voice, then select Create MP3 and Download MP3. It's free, and you don't need an account.
Do I need an account to download a text to speech MP3?
No. Every MP3 you make on this page downloads without an account. Sign up for a free Cartesia account when you want longer scripts or API access.
Can I use text to speech MP3 files for commercial purposes?
Yes, on the Pro plan and above, which include a commercial use license. See Cartesia's plans for what each one includes.
Which languages and voices can I use for text to speech MP3?
You can choose from 40+ languages, including English, Spanish, Hindi, Japanese and Arabic, each with its own voices. English, Spanish and French also come in regional accents, such as British English and Mexican Spanish.
How many characters can I convert to MP3 for free?
Up to 500 characters per MP3 on this page. For longer scripts, such as a course module or an audiobook chapter, generate the audio in the Cartesia playground or through the API.
Should I use MP3 or WAV?
MP3 files are small and play in every browser and audio app. WAV is uncompressed, so it suits audio editing. This page makes MP3s, and the API returns MP3, WAV or raw PCM.
What sample rate and bit rate are the text to speech MP3 files?
Each file is a 44.1 kHz MP3 at 128 kbps, the same settings as the API example on this page.
How do I get an MP3 from the Cartesia API?
Call the Text-to-Speech Bytes endpoint with output_format set to {"container":"mp3","sample_rate":44100,"bit_rate":128000}. The response is the MP3 itself, so save the bytes to a file ending in .mp3.
Can I make a voicemail greeting MP3 with text to speech?
Yes. Type the greeting, download the MP3 and upload it to your phone system. The voicemail greeting generator also gives you ready-made scripts to start from.
Get started today
Talk to an expert.
Connect with a member of our team and learn how Cartesia can help you build world-class voice experiences.
Start building.
Access our models via API and bring a voice agent into production in minutes.