Struct AudioTranscriptionConfig 

#[non_exhaustive]
pub struct AudioTranscriptionConfig {
    pub language_codes: Option<Vec<String>>,
    pub custom_vocabulary: Option<Vec<String>>,
}

Audio transcription settings, for the user’s audio (inputAudioTranscription) or the model’s (outputAudioTranscription).

The default — every field unset — asks for transcription with the server’s defaults, which is what an empty {} on the wire means.

let config = AudioTranscriptionConfig::default()
    .language_codes(["en-US", "es-US"])
    .custom_vocabulary(["ORD-8472", "QwikPay"]);
assert_eq!(
    serde_json::to_value(&config).unwrap(),
    serde_json::json!({
        "languageCodes": ["en-US", "es-US"],
        "customVocabulary": ["ORD-8472", "QwikPay"],
    }),
);

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

language_codes: Option<Vec<String>>

BCP-47 language hints (e.g. "en-US"). Hints reduce misdetected languages, especially on short utterances.

custom_vocabulary: Option<Vec<String>>

Domain terms the recogniser should prefer — product names, SKUs, proper nouns (Gemini 3.8 Live).

Implementations

impl AudioTranscriptionConfig

pub fn language_codes<S: Into<String>>( self, codes: impl IntoIterator<Item = S>, ) -> Self

Set the BCP-47 language hints.

pub fn custom_vocabulary<S: Into<String>>( self, terms: impl IntoIterator<Item = S>, ) -> Self

Set the terms transcription is biased toward.

Trait Implementations

impl Clone for AudioTranscriptionConfig

fn clone(&self) -> AudioTranscriptionConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for AudioTranscriptionConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for AudioTranscriptionConfig

fn default() -> AudioTranscriptionConfig

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for AudioTranscriptionConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for AudioTranscriptionConfig

fn eq(&self, other: &AudioTranscriptionConfig) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for AudioTranscriptionConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Eq for AudioTranscriptionConfig

impl StructuralPartialEq for AudioTranscriptionConfig