38b78d8a4a
Swap the voice synthesis backend from chatterbox-fast (:8197 bespoke /tts)
to dots-tts (rednote-hilab dots.tts-soar, :8198 OpenAI-shaped
/v1/audio/speech), operator-directed after an A/B win. tts.py stays the
single swap seam.
- gateway body OpenAI-shaped: {input, voice, response_format, stream}
(was chatterbox {text, voice, format, stream})
- sample rate 24000 -> 48000 Hz (browser Web Audio SR)
- default voice glados_25s -> glados; donut voice carries over
- serialized single-consumer (satisfied by the existing DEC-5 lock)
- affect stays dropped (dots has no emotion knob, same as chatterbox)
DOTS_TTS_URL replaces CHATTERBOX_TTS_URL; RATATOSKR_TTS_URL override
unchanged. chatterbox-fast :8197 kept up as rollback. Contract amended
(donut_voiced_interview.contract.md). Live-verified end-to-end on :8765
(RIFF/WAVE 48kHz mono s16le through /api/tts). 520 tests green.
126 lines
5.1 KiB
Python
126 lines
5.1 KiB
Python
"""Tests for ratatoskr.tts — the STREAMING dots-tts gateway client.
|
|
|
|
tts_stream proxies the gateway's chunked response verbatim (no buffering, no header
|
|
rewrite — the placeholder-size streaming WAV is meant to be played progressively). It
|
|
is the sole synthesis primitive: dots streams a whole turn from one call, so there is
|
|
no client-side chunk-and-concatenate, and no affect dials (dots has no emotion knob).
|
|
The mid-stream degrade policy is folded in.
|
|
"""
|
|
|
|
import httpx
|
|
import pytest
|
|
import respx
|
|
|
|
from ratatoskr.tts import (
|
|
DOTS_TTS_URL,
|
|
TtsUnavailable,
|
|
gateway_body,
|
|
tts_stream,
|
|
)
|
|
|
|
_URL = "http://tts.example/v1/audio/speech"
|
|
# The gateway's streaming WAV bytes (placeholder 0xFFFFFFFF sizes). We pass them through
|
|
# untouched, so the content only has to round-trip.
|
|
_WAV = (
|
|
b"RIFF\xff\xff\xff\xffWAVEfmt \x10\x00\x00\x00" + b"\x00" * 20
|
|
+ b"data\xff\xff\xff\xff" + b"\x11\x22" * 64
|
|
)
|
|
|
|
|
|
async def _drain(gen) -> bytes:
|
|
out = b""
|
|
async for chunk in gen:
|
|
out += chunk
|
|
return out
|
|
|
|
|
|
class _RaisingByteStream(httpx.AsyncByteStream):
|
|
"""A 200-body stream that yields `head` then drops mid-stream (an httpx.ReadError, a
|
|
RequestError subclass) — models a gateway connection drop AFTER the response committed."""
|
|
|
|
def __init__(self, head: bytes) -> None:
|
|
self._head = head
|
|
|
|
async def __aiter__(self):
|
|
yield self._head
|
|
raise httpx.ReadError("mid-stream drop")
|
|
|
|
async def aclose(self) -> None:
|
|
pass
|
|
|
|
|
|
class TestGatewayBody:
|
|
def test_openai_dots_schema(self) -> None:
|
|
b = gateway_body("hi", "donut")
|
|
assert b["input"] == "hi" # OpenAI "input", not chatterbox "text"
|
|
assert b["voice"] == "donut"
|
|
assert b["response_format"] == "wav" # DEC-3 — "response_format", not "format"
|
|
assert b["stream"] is True # DEC-2 — play-as-it-arrives
|
|
|
|
def test_default_sampling_no_client_side_curbs(self) -> None:
|
|
# No client sampling curbs — the gateway's defaults govern (a client-side curb
|
|
# was counterproductive on the prior backend and dots exposes no such need).
|
|
b = gateway_body("a long turn", "donut")
|
|
for knob in ("temperature", "top_p", "top_k"):
|
|
assert knob not in b
|
|
|
|
def test_no_chatterbox_or_zonos_era_fields(self) -> None:
|
|
# The chatterbox bespoke names + Zonos-era fields are gone: no `text`/`format`
|
|
# (chatterbox), no `language` pin, no affect dials (DEC-7 retired).
|
|
b = gateway_body("hi", "glados")
|
|
for dead in ("text", "format", "language", "emotion_valence",
|
|
"emotion_arousal", "emotion_enabled", "emotion_strength"):
|
|
assert dead not in b
|
|
|
|
|
|
class TestTtsStream:
|
|
@respx.mock
|
|
async def test_streams_chunks_and_posts_openai_body(self) -> None:
|
|
route = respx.post(_URL).mock(return_value=httpx.Response(200, content=_WAV))
|
|
async with httpx.AsyncClient() as client:
|
|
out = await _drain(tts_stream("hello there", voice="donut", client=client, url=_URL))
|
|
assert out == _WAV # passed through verbatim — no header rewrite
|
|
import json as _json
|
|
|
|
body = _json.loads(route.calls.last.request.content)
|
|
assert body["input"] == "hello there"
|
|
assert body["voice"] == "donut"
|
|
assert body["response_format"] == "wav"
|
|
assert body["stream"] is True
|
|
|
|
@respx.mock
|
|
async def test_default_url_is_dots(self) -> None:
|
|
route = respx.post(DOTS_TTS_URL).mock(
|
|
return_value=httpx.Response(200, content=_WAV)
|
|
)
|
|
async with httpx.AsyncClient() as client:
|
|
await _drain(tts_stream("hi", voice="donut", client=client))
|
|
assert route.called # the module default points at the dots-tts gateway
|
|
|
|
@respx.mock
|
|
async def test_non_200_open_raises_before_any_chunk(self) -> None:
|
|
respx.post(_URL).mock(return_value=httpx.Response(500, content=b"boom"))
|
|
async with httpx.AsyncClient() as client:
|
|
with pytest.raises(TtsUnavailable) as exc:
|
|
await _drain(tts_stream("hi", voice="Cora", client=client, url=_URL))
|
|
assert exc.value.status == 500
|
|
|
|
@respx.mock
|
|
async def test_transport_error_on_open_raises(self) -> None:
|
|
respx.post(_URL).mock(side_effect=httpx.ConnectError("refused"))
|
|
async with httpx.AsyncClient() as client:
|
|
with pytest.raises(TtsUnavailable):
|
|
await _drain(tts_stream("hi", voice="Cora", client=client, url=_URL))
|
|
|
|
@respx.mock
|
|
async def test_mid_stream_drop_after_first_byte_degrades_not_raises(self) -> None:
|
|
# The 200 is committed once bytes flow; a later transport drop must DEGRADE
|
|
# (return what streamed), never raise — the pivot is yielded_any, folded in from
|
|
# the retired tts_stream_long. Keeps a committed StreamingResponse from an ASGI trace.
|
|
respx.post(_URL).mock(
|
|
return_value=httpx.Response(200, stream=_RaisingByteStream(_WAV))
|
|
)
|
|
async with httpx.AsyncClient() as client:
|
|
out = await _drain(tts_stream("hi", voice="donut", client=client, url=_URL))
|
|
assert out == _WAV # head kept, no raise
|