Add TTS voice deletion, async speech jobs, voice-list cache, ref-seconds name tags

- DELETE /tts/voices/{name}: remove a cloned voice via the llama-swap
  passthrough (upstream chatterbox-tts-api exposes DELETE /voices/{name}).
- POST/GET/DELETE /tts/speech/jobs: durable job flow for long syntheses —
  dispatch returns 202 + job id, the synth queues on the GPU permit instead
  of fast-failing 429, and clients poll for the result (kept ~10 min).
- GET /tts/voices now serves an in-memory cache so listing voices doesn't
  make llama-swap spin up the TTS model (evicting the resident LLM);
  invalidated on create/delete, ?refresh=1 forces an upstream re-query.
- Created voice names are tagged with LLAMA_SWAP_TTS_REF_SECONDS (e.g.
  grandma-30s) so the library shows which ref length produced each clone.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

src/main.rs

@@ -364,9 +364,13 @@ fn main() -> std::io::Result<()> {
                 .service(ai::rate_insight_handler)
                 .service(ai::export_training_data_handler)
                 .service(ai::tts_speech_handler)
+                .service(ai::create_speech_job_handler)
+                .service(ai::speech_job_status_handler)
+                .service(ai::cancel_speech_job_handler)
                 .service(ai::list_voices_handler)
                 .service(ai::create_voice_upload_handler)
                 .service(ai::create_voice_from_library_handler)
+                .service(ai::delete_voice_handler)
                 .service(libraries::list_libraries)
                 .service(libraries::patch_library)
                 .add_feature(add_tag_services::<_, SqliteTagDao>)