Guides

TTS Release Notes

The following sections list every released version of TTS, newest first. Each section comes from the monthly OCP® Release Notes page named in its Released line.

TTS 3.4.2

Released: October 2026

US1

US2

EU1

—

—

—

  • General security improvements.


TTS 3.4.1

Released: October 2026

US1

US2

EU1

—

—

—

  • If the voice cannot produce a clean result after retrying, the request now fails with an error instead of returning unchecked audio.

  • The voice now retries a sentence at most once, reducing delay.

  • The spoken notice when the voice retries is now "Apologies, let me try again." in all ten languages, replacing the wording that mentioned network issues.


TTS 3.4.0

Released: October 2026

US1

US2

EU1

October 19, 2026

Rolled-forward

October 29, 2026

New features

  • German (de-DE) verbalization support.

  • European Portuguese (pt-PT) verbalization support.

  • Canadian English (en-CA) verbalization support.

  • More natural flow between sentences. Our latest voice family now takes the previous sentence into account when speaking the next one, so intonation carries across a multi-sentence prompt and across consecutive turns.

  • Better respect for punctuation. Commas and full stops now shape pauses and intonation more faithfully.

  • Audible notice when synthesis retries. If the voice has to restart a sentence, it now also says a short apology in the request's language ("Apologies, I am experiencing some network issues. Let me try again.") instead of pausing silently.

Email and URL verbalization

  • The part of an email address before the @ is read as words where it makes sense, with digits read one by one ("omilia_19@" → "omilia underscore one nine"). Short code-like parts are still spelled out.

  • Email addresses and URLs written in capitals are now recognized ("INFO@EXAMPLE.COM").

  • English "www" is read "W W W", with more stable delivery.

  • Missing symbol names added for French and Ukrainian URLs and emails.

  • Greek: words in web and email addresses are read more accurately, and "ftp" is spelled out.

English

  • "Ave" → "avenue".

  • The ™ and ℠ signs are no longer read aloud as "TM" / "SM".

  • en-GB uses British spelling for metric units ("kilometre", "litre").

French

  • Canadian French (fr-CA) brought up to the same standard as US English for numbers, units, telephone numbers, postal codes and addresses.

  • Month abbreviations ("janv." → "janvier"), "no." before a number ("numéro") and "par ex." are expanded.

  • Hyphenated names are read whole on our latest voice family ("Jean-Pierre" no longer reads "tiret").

Spanish

  • Month abbreviations ("ene." → "enero") and "número" forms ("n.º", "núm.", "nro.") are expanded on all Spanish locales.

  • Latin American Spanish: "w" is read as one word, "dobleú".

Greek

  • Time ranges read naturally ("06:00-22:00" → "έξι προ μεσημβρίας έως δέκα μετά μεσημβρίαν"), including ranges with an en dash or with ΠΜ/ΜΜ markers.

Behaviour changes

  • Hyphenated digit groups now read the same on every locale. On Brazilian Portuguese and French, "4-2-1-4" is read as one group with no pause after each digit, and longer groups are read as numbers.

Audio quality

  • At faster or slower speaking rates, the pauses at the start and end of the audio no longer stretch or shrink with the speech.


TTS 3.3.0

Released: September 2026

US1

US2

EU1

Rolled-forward

Rolled-forward

Rolled-forward

Highlights & Improvements

  • New Peninsular Spanish (es-ES), Mexican Spanish (es-MX) and Brazilian Portuguese (pt-BR) verbalization support, alongside new Lexis voices in respective locales.

  • US telephone numbers read correctly. Numbers written without a leading 1- are now recognized instead of being mis-grouped with the dash read aloud; a country code in parentheses or with a + no longer leaks a literal bracket, plus sign or a stray "dash"; and a short pause now separates the number groups instead of running them together.

  • Closing brackets are no longer dropped from input. Every closing round, square and curly bracket was being silently removed from incoming text before synthesis.


TTS 3.2.3

Released: September 2026

US1

US2

EU1

Rolled-forward

Rolled-forward

Rolled-forward

Highlights & Improvements

  • Improved Fraction and Measurement Pronunciation: Fractions written as x/y are now read as fractions instead of calendar dates, without requiring SSML markup. 1/2 kg reads as “one half kilogram” and 13/16 }}as “thirteen sixteenths”, with correct singular/plural units ({{5/2 hours → “five halves hours”) and compound units (3/4 km/h → “three fourths kilometer per hour”). Date-shaped values with no following unit (e.g. 1/2) continue to be read as dates. Use the spelled-out unit (3/16 inches) where a fraction is intended.​​​​​​​​​​​​​​​​

  • Smoother Spelled-Out Text & Alphanumeric Sequences: Enhanced speech synthesis stability and confidence for spelled-out text (e.g., spelled names, email addresses, license plates) and alphanumeric/SKU codes (e.g., VS504).

  • Accurate Decimal Normalization: Added support for decimal numbers written without a leading zero (e.g., .95 l is properly normalized and read as "zero point nine five liters")..


TTS 3.2.1

Released: August 2026

US1

US2

EU1

September 7, 2026

September 16, 2026

September 8, 2026

Stability (Lexis voices)

  • GPU crashes observed under sustained high-concurrency traffic no longer occur.

  • If a GPU-level error does happen, the service now reports itself as unavailable instead of continuing to accept traffic it cannot serve, so the affected instance is restarted automatically and recovers on its own. Previously, it stayed in service, failed every request, and needed a manual restart.

  • The hallucination guardrail is now on by default. Audio that runs far longer than the input text can justify is cut short, and the prompt is retried. The retry can be preceded by a short apology (for example, "Sorry, let me try again."), configurable per deployment.

Verbalization

  • "Ave." is now read as "avenue", including when capitalized. The same fix covers other capitalized address abbreviations such as St. and Blvd.

  • Numeric sequences are now read three digits at a time, regardless of whether they are repeated or not.

  • Telephone numbers are read digit by digit in all supported locales, with two-zero groups spoken as multiples: "800" as "eight hundred", a trailing "1400" as "fourteen hundred".

Prosody

  • Unexpected pauses in the middle of a sentence, most noticeable in Greek, are reduced. Where a long sentence still has to be broken up, the break is placed at a comma instead of in the middle of a clause, so the words either side of the break are no longer run together.

  • This is a mitigation rather than a complete fix. The underlying cause, sentence length being estimated before the text is verbalized, requires a structural change to the engine and is planned for a following release.


TTS 3.2.0

Released: August 2026

US1

US2

EU1

Rolled-forward

Rolled-forward

Rolled-forward

Spanish pronunciation & verbalization fixes (es-US, es-CO)

  • Chained spelled-out letters are now clearly separated.

  • Capitalized abbreviations opening a sentence are handled correctly.

  • Unit designators after address abbreviations are read properly as part of the address.

Colombian Spanish (es-CO) number & currency fixes

  • Decimal values with units read correctly: "2,5Gb" → "dos coma cinco gigabits" (previously "veinticinco gigabits").

  • Numbers written with a period are no longer mistaken for dates.

  • Amounts under one unit read as the subunit: "$0,01" → "un centavo" (previously "signo de dólar cero coma cero uno").

  • Decimal numbers using the Colombian "," separator are read as "coma" instead of "punto".

Lexis voices only: en-US, en-GB, fr-CA, es-US, es-CO

  • Punctuation is no longer preceded by an audible gap.

  • Long runs of the same repeated digit are correctly handled and do not result in hallucinated audio.


TTS 3.1.0

Released: July 2026

US1

US2

EU1

July 29, 2026

August 6, 2026

August 3, 2026

New Lexis voices - https://omilia.com/platform/voice-agents/lexis/

  • New Spanish (Colombia) CX Ambassador personas from our latest Lexis voice family: María v.3.0.0 and Andrés v.3.0.0 (Trusted Advisor)

Pan-locale verbalization change for Lexis voices only: en-US, en-GB, fr-CA, es-US, es-CO

  • Multi-word acronyms and all-caps words are no longer spelled out letter-by-letter. Instead they are spoken as a whole word.

New Lexis locale verbalization support

American Spanish (es-US) pronunciation & verbalization fixes

  • Abbreviation "dr." now reads as "doctor" (previously "médico").

  • Symbols read naturally: "%" → "por ciento", "+" → "más", "&" → "y".

  • Percentages like "20%" read as "veinte por ciento".

  • Hyphenated words such as "check-in" no longer read the hyphen aloud.

  • Large quantities read correctly: "millones", "billones" (no longer "millónes").

  • A sentence-initial "Y" is now read as the word "y" instead of being spelled out.

  • New Spanish and US-style address abbreviations are expanded (e.g. "ave." → "avenue", "blvd." → "boulevard").

SSML improvements and support on our Lexis voices - SSML tags support of Omilia TTS

  • <prosody> , <rate> , <volume> : Speaking-rate control on our latest voices: adjust pace with (e.g. slow, fast, or a numeric factor), as well as volume control

el-GR improvements for existing voices - Deprecated / TTS Verbalization Guide and Specification for el-GR

  • Improved pronunciation and word stress of embedded English words.

Security

  • General security vulnerability fixes.


TTS 3.0.0

Released: July 2026

US1

US2

EU1

June 30, 2026

Rolled-forward

Rolled-forward

Beta

Lexis is Omilia’s new generative text-to-speech model, built to unlock the most authentic Customer Service experiences.

Speech with the expressiveness, warmth, timing, and emotion of a skilled human agent, generated in real time, entirely inside your own platform and adapting to the context and the stakes of every conversation, in many languages.

  • Model: Lexis v1.0.0

  • CX Ambassador Persona library: en-US - Rob v1.0.0

  • SSML support: <break>

New features

  • New voice family Lexis. Adds support for our newest, more natural-sounding voice technology.

  • New SSML <sub> tag. You can now control exactly how a word or abbreviation is spoken by supplying a spoken-form alias. Example: <sub alias="World Health Organization">WHO</sub> is read as "World Health Organization" while "WHO" stays in your text.

For more information go to SSML tags support of Omilia TTS.


TTS 2.8.1

Released: May 2026

US1

US2

EU1

May 25, 2026

June 3, 2026

May 28, 2026

Stability

  • Fixed a rare audio-generation failure on prompts of certain lengths. Affected prompts now synthesize normally.


TTS 2.8.0

Released: May 2026

US1

US2

EU1

May 14, 2026

May 20, 2026

May 11, 2026

English (en-US, en-AU) verbalization improvements

  • Smarter context-aware abbreviation handling in a sentence for English: Common short forms like gov., co., org., no., and in. behave according to the context of the sentence. For example the word location in the sentence - in the middle or the end of the sentence, changes the way an abbreviation is treated.

    • Example Sentences: "Say yes or no." vs "Share the no. 8 item on your list"

    • In in the first sentence, it no longer reads as "Say yes or number".

For more information, go to TTS Verbalization Guide and Specification for en-US.

Greek (el-GR) verbalization & pronunciation improvements

  • Currency amounts with 3+ decimal digits now read the decimal portion as a whole number (e.g., "1,623 ευρώ" → "ένα κόμμα εξακόσια εικοσιτρία ευρώ").

  • Decimal currency with text-form words is read naturally (e.g., "1,99 ευρώ" → "ένα ευρώ και ενενηνταεννέα λεπτά").

  • Digit-prefix ψήφι- compounds verbalize correctly (e.g., "9ψήφιο" → "εννιαψήφιο", "14ψήφιο" → "δεκατετραψήφιο").

  • Percentages followed by punctuation, like a full stop (.), now verbalize correctly (e.g., "24%." → "εικοσιτέσσερα τοις εκατό.").

  • Numbers (tens) have a more natural delivery

  • Article references like "9.2α" are verbalized correctly (e.g., "εννέα τελεία δύο άλφα").

  • GB and MB are read as "γιγαμπάιτ" / "μεγαμπάιτ" in both attached and standalone forms. (e.g for "4GB" and "GB")

  • Gender agreement is corrected for feminine-singular -ά nouns (e.g., "1 φορά" → "μία φορά"); short function words like "ή" no longer feminize the preceding number.

For more information, go to TTS Verbalization Guide and Specification for el-GR.

SSML <phoneme> tag & stability fixes

  • Phoneme markers are now correctly applied across all supported languages and voices

    • Example: <phoneme alphabet="ipa" ph="ˈanTropos">άνθρωπος</phoneme> and <phoneme alphabet="x-sampa" ph='"anTropos'>…</phoneme> now correctly pronounced

  • Multi-word phoneme markers now respect word boundaries.

    • Example: <phoneme alphabet="ipa" ph="fipi ˈa">fipia</phoneme> (a pronunciation override containing a space) is now pronounced properly

  • Support for very long prompts >800 characters, that contain many <phoneme> markers. For example, a long sentence with a dozen or more <phoneme> overrides, previously prone to truncation mid-sentence on some voices, now synthesizes in full.

For more information on SSML support, go to SSML tags support of Omilia TTS.

Security

  • General security vulnerability fixes


TTS 2.7.0

Released: April 2026

US1

US2

EU1

April 23, 2026

May 4, 2026

April 23, 2026

New Features

  • Ukrainian (uk-UA) - Olesia Female voice v1.0.0: Our new female Omilia Ukrainian voice, Olesia is now available. It has a professional, grounded style.

Updates

  • English (en-US) - Oliver Happy v1.0.5 and Oliver v1.1.3 : Lexicon extension

  • Greek (el-GR) - Nefeli v1.1.3: Lexicon extension

  • English (en-US) - SSML dash handling : Dashes within SSML tags are now correctly parsed and handled to ensure audio is correctly being generated

  • Security patches

  • Improved URL and email verbalization across all locales to ensure correct, natural-sounding output. The following improvements are required:

    • Slash ( / ) and dash ( - ) pronounced (locale-specific) - Change
      Locale(s): en-GB
      Input example: https://www.example.com/my-page
      Old output: "slash" and "dash"
      New output: "forward slash" and "hyphen"

    • Equal sign (=) pronounced in URLs - Addition
      Locale(s): All (English & Greek)
      Input example: https://www.ocp.ai/input=?$ad
      Old output: "ocp dot ai slash input question mark dollar sign ad" (equal sign skipped)
      New output: "ocp dot ai slash input equal sign question mark dollar sign ad"

    • FTP prefix pronunciation fix in FTP URLs - Bug fix
      Locale(s): All
      Input example: ftp://ftp.example.com/resource
      Old output: "ftp colon double slash tifi dot example dot com slash resource"
      New output: "ftp colon double slash ftp dot example dot com slash resource"

    • Port number colon in URLs - Addition
      Locale(s): All
      Input example: http://example.com:8080/path/to/resource
      Old output: "example dot com 8080 slash path slash to slash resource"
      New output: "example dot com colon 8080 slash path slash to slash resource"

    • IP address URLs pronounced clearly - Bug fix
      Locale(s): All
      Input example: http://123.123.123.123/path/to/resource
      Old output: unclear / not understandable
      New output: "one hundred twenty three dot one hundred twenty three dot one hundred twenty three dot one hundred twenty three slash path slash to slash resource"

    • Percent-encoded (% … % ) characters pronounced in URLs - Addition
      Locale(s): All
      Input example: http://example.com/path%20with%20spaces
      Old output: "example dot com slash path twenty with twenty spaces" (percent sign ignored)
      New output: "example dot com slash path percent two zero with percent two zero spaces"


TTS 2.6.2

Released: March 2026

US1

US2

EU1

Rolled-forward

Rolled-forward

Rolled-forward

This hot fix release addresses bug fixes reported for the en-AU voices.
[Applied on Private Cloud (OPC) environments only]

Pronunciation fixes

  • "Do not" and AM/PM abbreviations are now spoken correctly.

  • A capital "A" at the start of a sentence is now read as the article "a," not spelled out.

  • Special characters in input text no longer cause unexpected pronunciation errors.

Timing & pacing

  • Reference numbers read character-by-character now have consistent, even pacing.

  • Phone numbers and digit strings are spoken at a natural speed.

Language quality

  • Dates are now spoken in Australian format (for example, "the 6th of March, 2026").

  • Words with context-dependent pronunciation (for example, record as noun vs. verb) are handled correctly.

  • Expanded vocabulary and improved handling of uncommon words.

For more information, see the Omilia TTS Solution.


TTS 2.6.1

Released: March 2026

US1

US2

EU1

March 26, 2026

April 21, 2026

March 26, 2026

  • Greek numbers with leading zeros are now spoken individually (for example, "007" → "μηδέν μηδέν επτά") [Applied on Frankfurt environment only]

Please see related deprecation notes in TTS Deprecation Notes - Verbalization Changes.

  • Fixed Greek number gender agreement so numbers match the gender of the following noun (for example, "4 μονάδες" → "τέσσερις μονάδες" instead of "τέσσερα μονάδες").

  • Smoother pronunciation of Greek compound numbers (21–99).

  • Fixed letter spelling in "letter, like word" / "γράμμα, όπως λέξη" patterns for en-US and el-GR.

  • Improved stability under high concurrent traffic of some voices.

  • Security vulnerability fixes.

For more information, see the Omilia TTS Solution.


TTS 2.6.0

Released: February 2026

US1

US2

EU1

February 25, 2026

Rolled-forward

February 26, 2026

Please read TTS Deprecation Notes - Verbalization Changes for more details.

  • Added support for SSML <phoneme> tag (IPA and X-SAMPA) for precise custom pronunciations (link).

  • Improved pronunciation of "the" depending on the following word.

  • Removed pauses caused by trailing apostrophes (for example, "customers' spending").

  • Accepted SSML <lang> tag (doesn't influence verbalization).

  • Fixed handling of prompts that contain only a single <break>.

  • Fixed wrong pronunciation of some Greek words and added missing English words for el-GR Nefeli.

For more information, see the Omilia TTS Solution.

‌


TTS 2.5.6

Released: January 2026

US1

US2

EU1

January 20, 2026

Rolled-forward

January 20, 2026

  • Security updates


TTS v2.5.5

Released: November 2025

US1

US2

EU1

November 3, 2025

Rolled-forward

November 3, 2025

Fixes and Improvements

  • Fix pronunciation of cases “I, like India”

  • Verbalize simple numbers as a whole instead of digit-by-digit in English

  • Correct verbalization of ‘&’ symbol as ‘and’

  • Fix issue with word goodbye - Oliver Happy

  • Fix mispronunciation of time formats like ‘8PM’ and ‘8:00pm’

  • Fix pronunciation in say-as “digits” SSML and in consecutive breaks SSML tags

  • Verbalize correctly plural abbreviations like “PINs”


TTS v2.4.5

Released: April 2025

US1

US2

EU1

Rolled-forward

Rolled-forward

Rolled-forward

  • General improvements in Omilia's el-GR Female model

    • Fix the way dates are verbalized

    • Fix the way "&" is pronounced

    • Issue with numbers being spelled out

  • New el-GR Female model upgrade to version 1.1.0.


TTS v2.4.3

Released: March 2025

US1

US2

EU1

Rolled-forward

Rolled-forward

Rolled-forward

  • Improvements on el-GR Female TTS model

  • Optimisation on the tts-engine

  • Security Fixes

For more information, go to Omilia TTS Solution .