step2

src/tts/fish_audio.rs

@@ -5,6 +5,12 @@
 //! mixer's output rate, so samples are pushed directly into the TTS queue
 //! without resampling. A [`CancellationToken`] allows immediate interruption
 //! (barge-in).
+//!
+//! Drama 3 can sound overly theatrical on some references. Two mitigations are
+//! applied here, both configurable from the environment: optional sampling
+//! knobs (`temperature` / `top_p` / `top_k`) that trim the tails of the
+//! acoustic token distribution, and a neutral style tag prepended to untagged
+//! requests so plain LLM prose is read in a conversational register.
 
 use crate::audio::SampleRingBuffer;
 use crate::config::Config;
@@ -26,6 +32,11 @@ struct Reference {
 }
 
 /// Request body for the SGLang `/v1/audio/speech` endpoint.
+///
+/// Sampling knobs are optional and only serialized when set. Drama 3 accepts
+/// `temperature`, `top_p` and `top_k` at this level; `repetition_penalty` is
+/// deliberately never sent because this server rejects any value other than
+/// `1.0` (`Drama 3 request: repetition_penalty must be 1.0`).
 #[derive(Debug, Serialize)]
 struct SpeechRequest<'a> {
     model: &'a str,
@@ -35,6 +46,12 @@ struct SpeechRequest<'a> {
     stream: bool,
     #[serde(skip_serializing_if = "Option::is_none")]
     references: Option<Vec<Reference>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    temperature: Option<f32>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    top_p: Option<f32>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    top_k: Option<u32>,
 }
 
 /// Streaming TTS client backed by Fish Audio / SGLang-Omni Drama 3.
@@ -46,6 +63,12 @@ pub struct FishAudioTts {
     voice: String,
     /// Current voice-cloning reference (config default, overridable at runtime).
     reference: Arc<parking_lot::RwLock<Option<Reference>>>,
+    /// Optional sampling overrides (de-emphasis of the recitative register).
+    temperature: Option<f32>,
+    top_p: Option<f32>,
+    top_k: Option<u32>,
+    /// Neutral style tag prepended to untagged synthesis requests.
+    style_tag: String,
 }
 
 impl FishAudioTts {
@@ -61,6 +84,13 @@ impl FishAudioTts {
                 "TTS voice-cloning reference configured"
             );
         }
+        info!(
+            temperature = ?config.tts_temperature,
+            top_p = ?config.tts_top_p,
+            top_k = ?config.tts_top_k,
+            style_tag = %config.tts_style_tag,
+            "TTS de-emphasis settings"
+        );
         Self {
             http: Client::builder()
                 .build()
@@ -69,6 +99,23 @@ impl FishAudioTts {
             model: config.tts_model.clone(),
             voice: config.tts_voice.clone(),
             reference: Arc::new(parking_lot::RwLock::new(reference)),
+            temperature: config.tts_temperature,
+            top_p: config.tts_top_p,
+            top_k: config.tts_top_k,
+            style_tag: config.tts_style_tag.clone(),
+        }
+    }
+
+    /// The text actually sent to the model: the configured neutral style tag is
+    /// prepended unless the text already opens with a style tag or the tag is
+    /// disabled. LLM replies carry no tags, so they get de-emphasized; clip
+    /// banks that start with their own tag are left untouched.
+    fn styled<'a>(&self, text: &'a str) -> std::borrow::Cow<'a, str> {
+        let tag = self.style_tag.trim();
+        if tag.is_empty() || text.trim_start().starts_with('[') {
+            std::borrow::Cow::Borrowed(text)
+        } else {
+            std::borrow::Cow::Owned(format!("{tag} {text}"))
         }
     }
 
@@ -107,14 +154,18 @@ impl TtsEngine for FishAudioTts {
         cancel: &CancellationToken,
     ) -> Result<()> {
         let references = self.reference.read().clone().map(|r| vec![r]);
+        let input = self.styled(text);
 
         let body = SpeechRequest {
             model: &self.model,
-            input: text,
+            input: &input,
             voice: &self.voice,
             response_format: "pcm",
             stream: true,
             references,
+            temperature: self.temperature,
+            top_p: self.top_p,
+            top_k: self.top_k,
         };
 
         info!(model = %self.model, text_len = text.len(), "SGLang TTS request");
@@ -125,7 +176,11 @@ impl TtsEngine for FishAudioTts {
             response_format = "pcm",
             stream = true,
             has_reference = body.references.is_some(),
-            text = %text,
+            temperature = ?self.temperature,
+            top_p = ?self.top_p,
+            top_k = ?self.top_k,
+            styled = input.len() != text.len(),
+            text = %input,
             "TTS request dispatched"
         );