feat(terra): luna speaks with ElevenLabs v4 turbo
eleven_v4_turbo is the new default, same price per character as
v3_conversational. v4 also streams over Text to Dialogue, so the switch is
now uses_dialogue() for both. Audio tags may carry free-text directions
("[whispers, in a German accent]"): commas and apostrophes allowed, up to
80 chars. The voice prompt and luna-soul.md teach her the wider tag set,
including in text_to_speech voice notes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -82,7 +82,7 @@ impl Config {
|
||||
|
||||
eleven_key: secret("LUNA_ELEVENLABS_KEY_FILE")?,
|
||||
voice_id: env("LUNA_VOICE_ID")?,
|
||||
tts_model: env_or("LUNA_TTS_MODEL", "eleven_v3_conversational"),
|
||||
tts_model: env_or("LUNA_TTS_MODEL", "eleven_v4_turbo"),
|
||||
|
||||
whisper_bin: env_or("LUNA_WHISPER_BIN", "whisper-cli"),
|
||||
whisper_model: PathBuf::from(env("LUNA_WHISPER_MODEL")?),
|
||||
|
||||
@@ -481,7 +481,7 @@ async fn turn(
|
||||
voice_id: cfg.voice_id.clone(),
|
||||
model: cfg.tts_model.clone(),
|
||||
};
|
||||
let keep_tags = tts_cfg.is_v3();
|
||||
let keep_tags = tts_cfg.uses_dialogue();
|
||||
let speech = tokio::spawn({
|
||||
async move { tts::speak(&tts_cfg, sentence_rx, event_tx).await }
|
||||
});
|
||||
|
||||
+31
-13
@@ -23,10 +23,10 @@ pub struct TtsConfig {
|
||||
}
|
||||
|
||||
impl TtsConfig {
|
||||
/// v3 is not served on the TTS websocket at all; it streams only over
|
||||
/// Text to Dialogue, a different protocol.
|
||||
pub fn is_v3(&self) -> bool {
|
||||
self.model.starts_with("eleven_v3")
|
||||
/// v3 and v4 are not served on the TTS websocket at all; they stream only
|
||||
/// over Text to Dialogue, a different protocol. Only these perform tags.
|
||||
pub fn uses_dialogue(&self) -> bool {
|
||||
self.model.starts_with("eleven_v3") || self.model.starts_with("eleven_v4")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -60,7 +60,7 @@ pub async fn speak(
|
||||
sentences: mpsc::Receiver<String>,
|
||||
events: mpsc::Sender<SpeechEvent>,
|
||||
) -> Result<()> {
|
||||
if cfg.is_v3() {
|
||||
if cfg.uses_dialogue() {
|
||||
speak_dialogue(cfg, sentences, events).await
|
||||
} else {
|
||||
speak_tts(cfg, sentences, events).await
|
||||
@@ -186,7 +186,7 @@ async fn read_audio(
|
||||
// Alignment times may be per-chunk or cumulative depending on the
|
||||
// model; `emitted_ms` lets us normalise either into one timeline.
|
||||
let mut emitted_ms: u32 = 0;
|
||||
// v3 audio tags come back as characters, and one can straddle chunks.
|
||||
// Audio tags come back as characters, and one can straddle chunks.
|
||||
let mut in_tag = false;
|
||||
let mut result = Ok(());
|
||||
while let Some(Ok(msg)) = source.next().await {
|
||||
@@ -266,7 +266,7 @@ fn absolutize(starts: &[i64], emitted_ms: u32) -> Vec<i64> {
|
||||
pub struct SentenceSplitter {
|
||||
buf: String,
|
||||
in_think: bool,
|
||||
/// Whether v3 audio tags survive to the synthesiser or are dropped.
|
||||
/// Whether audio tags survive to the synthesiser or are dropped.
|
||||
keep_tags: bool,
|
||||
}
|
||||
|
||||
@@ -342,17 +342,17 @@ fn drain_sentences(buf: &mut String, force: bool, keep_tags: bool) -> Vec<String
|
||||
out
|
||||
}
|
||||
|
||||
/// Byte index just past a v3 audio tag starting at `i` ("[laughs]",
|
||||
/// "[clears throat]"), if there is one. Letters and spaces only, so
|
||||
/// "[1]" or a markdown link stays ordinary noise.
|
||||
/// Byte index just past an audio tag starting at `i` ("[laughs]",
|
||||
/// "[whispers, in a German accent]"), if there is one. No digits, so "[1]"
|
||||
/// stays ordinary noise; the length cap keeps a bracketed sentence out.
|
||||
fn tag_end(s: &str, i: usize) -> Option<usize> {
|
||||
let rest = s[i..].strip_prefix('[')?;
|
||||
let close = rest.find(']')?;
|
||||
let body = &rest[..close];
|
||||
let end = i + 1 + close + 1;
|
||||
let ok = !body.trim().is_empty()
|
||||
&& body.len() <= 40
|
||||
&& body.chars().all(|c| c.is_alphabetic() || c == ' ' || c == '-')
|
||||
&& body.len() <= 80
|
||||
&& body.chars().all(|c| c.is_alphabetic() || matches!(c, ' ' | '-' | ',' | '\''))
|
||||
&& !s[end..].starts_with('(');
|
||||
ok.then_some(end)
|
||||
}
|
||||
@@ -491,20 +491,38 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn audio_tags_survive_for_v3_only() {
|
||||
fn audio_tags_survive_for_dialogue_models_only() {
|
||||
let s = "[laughs]Fine, boss. [clears throat] Na gut.";
|
||||
assert_eq!(clean_for_speech(s, true), "[laughs] Fine, boss. [clears throat] Na gut.");
|
||||
assert_eq!(clean_for_speech(s, false), "Fine, boss. Na gut.");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn free_text_directions_are_tags() {
|
||||
let s = "[whispers, in a German accent] Na gut. [like she's half asleep] Okay.";
|
||||
assert_eq!(clean_for_speech(s, true), s);
|
||||
assert_eq!(clean_for_speech(s, false), "Na gut. Okay.");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn brackets_that_are_not_tags_stay_noise() {
|
||||
assert_eq!(clean_for_speech("see [1] and [the docs](x)", true), "see 1 and the docs x");
|
||||
assert_eq!(clean_for_speech("see [1, 2]", true), "see 1, 2");
|
||||
assert_eq!(clean_for_speech("[see above, then reboot](x)", true), "see above, then reboot x");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn captions_hide_tags() {
|
||||
assert_eq!(strip_tags("[sighs] Okay, boss."), "Okay, boss.");
|
||||
assert_eq!(strip_tags("[whispers, in a German accent] Na gut."), "Na gut.");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn v4_streams_over_dialogue() {
|
||||
let cfg = |m: &str| TtsConfig { key: String::new(), voice_id: String::new(), model: m.into() };
|
||||
assert!(cfg("eleven_v4_turbo").uses_dialogue());
|
||||
assert!(cfg("eleven_v3_conversational").uses_dialogue());
|
||||
assert!(!cfg("eleven_flash_v2_5").uses_dialogue());
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
||||
Reference in New Issue
Block a user