SMS GSM-7 converter: remove characters that force Unicode

Paste an SMS to replace the characters that silently switch it to Unicode (UCS-2): curly quotes, long dashes, ellipses, non-breaking spaces and, if you allow it, accented letters that GSM-7 lacks, such as á or ç. The converter shows the encoding and segment count before and after, lists every replacement and the characters it cannot convert, such as emoji, and lets you copy the result.

Free · no sign-up · runs in your browser, nothing is uploaded

Your message

GSM-7 version

Replace accented letters GSM-7 lacks (á → a)

Before

GSM-7

0 segments · 0 characters

After

GSM-7

0 segments · 0 characters

Paste a message to see what changes.

Replacements

None.

Cannot be converted

None.

Runs entirely in your browser. Nothing you type, paste or upload is sent to MobileValidate or anyone else, and nothing is stored. The page counts one anonymous "tool used" event per visit (no numbers, no text), and sends nothing at all when your browser asks not to be tracked.

Don't pay to send to dead numbers

Fewer segments save money on every message; sending only to numbers that are live saves the whole message. Check whether numbers are live and which network they are on before you send.

Start free (20 free real checks) HLR lookup Carrier lookup

How it works

A message is sent in GSM-7 (160 characters, 153 per segment when longer) only when every character is in the GSM-7 alphabet. One character outside it switches the whole message to Unicode: 70 characters, 67 per segment. Text copied from a document or typed on a phone often carries such characters without anyone noticing.

Always replaced: curly quotes and apostrophes (’ “ ”) with straight ones, en and em dashes with a hyphen, the ellipsis (…) with three dots, non-breaking and thin spaces with a normal space, invisible zero-width characters removed, and a few symbols such as ™ written out.

Accents (your choice): GSM-7 has some accented letters (é, è, à, ü, ñ, Ç and others), which stay as they are. Letters it lacks lose their accent: á → a, ç → c, ł → l, œ → oe. Turn this off when an accent matters for meaning. Emoji and non-Latin scripts cannot be converted; they are listed, and the message stays Unicode while they are in it.

Segments are counted with the same packing as our SMS character counter: characters such as € count as two, and an escape pair is never split between segments.

Last updated 7 November 2026

Frequently asked questions

How do I stop my SMS from being sent as Unicode?

Remove every character outside the GSM-7 alphabet. The usual culprits are curly quotes and apostrophes, long dashes, ellipses and non-breaking spaces from word processors, plus emoji and some accented letters. Paste the text here and the converter replaces what it can and lists the rest.

Does replacing accents change my message?

It can. ç → c or á → a reads fine in most messages, but in some languages an accent changes a word. That is why accent replacement is a switch: leave it on for codes and notifications, turn it off when the wording matters more than the price.

How much can I save?

Often half or more. A 100-character message with one curly apostrophe is two Unicode segments; in GSM-7 it is one. Most networks and SMS providers bill each segment as one message, so the saving applies to every recipient.

Which characters cannot be converted?

Emoji, and letters of scripts that GSM-7 does not cover, such as Cyrillic, Arabic, Chinese or Hindi. Messages in those scripts need Unicode, or a national language shift table if your provider supports one.

Does my SMS provider do this automatically?

Some do, often as an option called smart encoding or character replacement, and each provider's table differs. Converting before you send means you see the exact text and segment count your recipients will get.

Is my message sent anywhere?

No. The conversion runs in your browser. Nothing you paste is sent to MobileValidate or anyone else, and nothing is stored.