Custom Pronunciations
Sonic supports inserting phonetic transcriptions for words that are hard to get right, like proper nouns or domain-specific terms.
How to insert phonemes
When using Sonic (whether through the playground, API, or client library) you can directly add Sonic-flavored IPA phonemes in the transcript. Just wrap them in <<>> and append each phoneme with a pipe |.
Sonic-flavored IPA
We’ve compiled a pronunciation guide for the style of IPA that works most effectively with Sonic.
Our model follows the English phonology article on Wikipedia for most phonemes, but in spots where our model requires different notation than you may expect, we’ve included a blue <= in the margins.
You can copy/paste some of these uncommon symbols from the original charts here.
Stresses and vowel length markers
Our model requires stress markers for first (ˈ) and second (ˌ) stressed syllables, which go directly before the vowel. We also use annotations for vowel length (ː). The model can also operate without them, but you will have noticeably better robustness and control when using them.
Usage example
Original input: "transcript": "Can I get jalapeño on that?"
Transformed input: "transcript": "Can I <<g|ˈɛ|t|>> <<h|ɑː|l|ˈə|p|eɪ|n|y|ˌoʊ|>> on that?"