enne2/qwentts.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

nit: realign endpoint tables on the widened voice routes

Browse Source
This commit is contained in:
Pascal
2026-07-17 21:13:57 +02:00
parent 0d1b25b863
commit d5b05efff7
2 changed files with 21 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/ARCHITECTURE.md
+15 -15
View File
@@ -628,24 +628,24 @@ Optional:
Endpoints :
```
POST /v1/audio/speech OAI text-to-speech; response_format "pcm"
streams s16le 24 kHz mono chunked as it is
generated, "wav" returns a one-shot RIFF file.
Optional sampling overrides ride in the same
body: seed, max_new_tokens, temperature,
top_k, top_p, repetition_penalty. Unset
fields keep the engine defaults, temperature
0 selects greedy decoding, the subtalker
mirrors the talker knobs
GET /v1/models single loaded model, using --alias when set
POST /v1/audio/speech OAI text-to-speech; response_format "pcm"
streams s16le 24 kHz mono chunked as it is
generated, "wav" returns a one-shot RIFF file.
Optional sampling overrides ride in the same
body: seed, max_new_tokens, temperature,
top_k, top_p, repetition_penalty. Unset
fields keep the engine defaults, temperature
0 selects greedy decoding, the subtalker
mirrors the talker knobs
GET /v1/models single loaded model, using --alias when set
GET /v1/audio/voices model speakers plus registered cloned voices
POST /v1/audio/voices register a cloned voice: {name, ref_text,
wav_b64} extracts server side through
qt_extract_voice_ref, {name, ref_text,
spk_b64, rvq_b64} takes the pre-extracted
latents verbatim
wav_b64} extracts server side through
qt_extract_voice_ref, {name, ref_text,
spk_b64, rvq_b64} takes the pre-extracted
latents verbatim
DELETE /v1/audio/voices/{name} drop a registered voice
GET /health liveness probe
GET /health liveness probe
```
A registered voice wins over a model speaker of the same name and
src/tts-server.h
+6 -6
View File
@@ -8,15 +8,15 @@
// are identical across projects ; only the adapter differs.
//
// Endpoints:
// POST /v1/audio/speech OAI text-to-speech
// GET /v1/models single loaded model
// POST /v1/audio/speech OAI text-to-speech
// GET /v1/models single loaded model
// GET /v1/audio/voices model speakers plus registered cloned voices
// POST /v1/audio/voices register a cloned voice: {name, ref_text,
// wav_b64} extracts server side, {name,
// ref_text, spk_b64, rvq_b64} takes
// pre-extracted latents verbatim
// wav_b64} extracts server side, {name,
// ref_text, spk_b64, rvq_b64} takes
// pre-extracted latents verbatim
// DELETE /v1/audio/voices/{name} drop a registered voice
// GET /health liveness probe
// GET /health liveness probe
//
// Audio out: response_format "pcm" streams s16le 24 kHz mono chunked as it
// is generated (real time), "wav" returns a one-shot RIFF file. pcm is the