Pronunciation dictionaries

How it works

A pronunciation dictionary is a list of per-organisation respelling rules applied to your text before synthesis. Create one in the console (Pronunciation), collect its id, and pass that id with any speech request — every rule in the dictionary applies to that request.

{
  "voice": "sv_enhdbrj5",
  "input": "Your SQL dashboard and HDFC statement are ready.",
  "pronunciation_dictionary_id": "fbdb2572-a0ed-4bf0-b83a-897411f95090"
}

Rules are respellings, not phonetics

The model reads letters, so rules are written the way the word should be read — SQL as sequel (or S Q L to spell it out), NASA as नासा. IPA and phoneme notation are not accepted; a rule pasted as /ˈnæsə/ is refused with an explanation of what to write instead.

Match options & language scope

• case_sensitive — match only with exact casing (default off: nasa matches NASA).
• word_boundaries — match whole words only (default on), Devanagari-aware.
• only_languages / except_languages — scope a rule to (or away from) specific request languages. One term may carry different rules at different scopes: HDFC read as एच डी एफ सी in Hindi and as H D F C everywhere else.

Using a dictionary in a request

Pass pronunciation_dictionary_id on speech requests or as a query parameter on the input-streaming WebSocket. Rules apply before normalization, and edits propagate to running infrastructure within seconds — no redeploys. The id is the dictionary’s UUID. An id the server cannot find is not an error: the workspace’s global rules apply instead and the response carries X-Svara-Dictionary: miss (the Python SDK warns).

Creating one over the API

Dictionaries can also be listed, read and created with your API key. Creation is all-or-nothing — one invalid rule fails the call and nothing is created — and returns 403 when the plan has no room, 409 for a duplicate name. Deleting stays in the console.

from svara import Svara, PronunciationRule

client = Svara()
d = client.pronunciation_dictionaries.create_from_rules(
    name="brand-terms",
    rules=[
        PronunciationRule("SQL", "sequel"),
        PronunciationRule("HDFC", "एच डी एफ सी", only_languages=["hi"]),
    ],
)
audio = client.speech.create(
    input="Your SQL dashboard is ready.", voice="sv_enhdbrj5",
    pronunciation_dictionary_id=d.id,
)