Labyricorn/voicebox
1
0
Fork 0
mirror of https://github.com/jamiepine/voicebox.git synced 2026-09-19 14:50:38 -07:00
Code Issues Packages Projects Releases Wiki Activity

feat: chunked TTS generation for long text (engine-agnostic)

Browse Source 
Text exceeding max_chunk_chars (default 800) is automatically split at
sentence boundaries, generated per-chunk, and concatenated with a 50ms
crossfade.  Works with all engines (Qwen, LuxTTS, Chatterbox, Turbo).

- Abbreviation-aware sentence splitter (Dr., Mr., e.g., decimals)
- CJK sentence-ending punctuation support
- Paralinguistic tag preservation ([laugh], [cough], etc.)
- Per-chunk seed variation to avoid correlated RNG artefacts
- Per-chunk Chatterbox trim (catches hallucination at each boundary)
- max_chunk_chars exposed as per-request param on GenerationRequest
- Text max_length raised to 50,000 characters

Closes #99
This commit is contained in:
James Pine
2026-03-13 06:21:34 -07:00
parent c12b5d6f0a
commit 70ca7f66cb
3 changed files with 329 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/models.py
+2 -1
View File
@@ -52,12 +52,13 @@ class ProfileSampleResponse(BaseModel):
class GenerationRequest(BaseModel):
"""Request model for voice generation."""
profile_id: str
text: str = Field(..., min_length=1, max_length=5000)
text: str = Field(..., min_length=1, max_length=50000)
language: str = Field(default="en", pattern="^(zh|en|ja|ko|de|fr|ru|pt|es|it|he)$")
seed: Optional[int] = Field(None, ge=0)
model_size: Optional[str] = Field(default="1.7B", pattern="^(1\\.7B|0\\.6B)$")
instruct: Optional[str] = Field(None, max_length=500)
engine: Optional[str] = Field(default="qwen", pattern="^(qwen|luxtts|chatterbox|chatterbox_turbo)$")
max_chunk_chars: int = Field(default=800, ge=100, le=5000, description="Max characters per chunk for long text splitting")
class GenerationResponse(BaseModel):