vh/ratatoskr
1
0
Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity

feat(tts): config-driven voices + two-voice dialogue/narration split (DEC-11)

Browse Source 
Voice assignment moves from the hardcoded server map to ~/.config/ratatoskr/
voices.json (per-agent voice + optional narration_voice). An agent with a
narration_voice gets a two-voice split: quoted speech in `voice`, narration in
`narration_voice`, synthesized per-span and stitched under one WAV header.

- new src/ratatoskr/voices.py: load_voice_config (degrade-not-crash),
  segment_dialogue (quote-based, straight + curly), resolve_voice_spans
- tts.py: tts_stream_stitched replaces tts_stream — serial per-span synth,
  span 0 verbatim, spans 1..N header-stripped -> one gapless 48kHz stream;
  a single-span list is a byte-identical passthrough (no single-voice regression)
- server.py: _tts_endpoint resolves spans from app.state.voice_config; the
  hardcoded _TTS_VOICE_MAP is retired; create_app gains a voice_config param
- entrypoint.py: loads voices.json at startup
- contract DEC-11 + INV-TTS-5/6/7; initial config donut->donut,
  sindra->miranda (dialogue) / emmie (narration)

Live-verified on :8765: Sindra mixed turn -> 2 dots calls (emmie+miranda)
stitched into one 48kHz WAV with a single RIFF header; Donut single-voice
unchanged. 545 tests green (incl. new test_voices.py).
This commit is contained in:
vh
2026-08-11 08:02:30 -07:00
parent 3e69bc9c01
commit 5c3d0ad010
10 changed files with 495 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_tts.py
+74 -21
View File
@@ -1,10 +1,10 @@
"""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.
tts_stream_stitched is the sole synthesis primitive: it synthesizes an ordered list of
(voice, text) spans serially into one continuous stream — the first span verbatim, later
spans header-stripped (DEC-11 two-voice split). A single-span list is a verbatim passthrough
(no buffering, no header rewrite), so the single-voice / dialogue-only case is unchanged. No
affect dials (dots has no emotion knob). The mid-stream degrade policy spans the sequence.
"""
import httpx
@@ -15,7 +15,7 @@ from ratatoskr.tts import (
DOTS_TTS_URL,
TtsUnavailable,
gateway_body,
tts_stream,
tts_stream_stitched,
)
_URL = "http://tts.example/v1/audio/speech"
@@ -25,6 +25,12 @@ _WAV = (
b"RIFF\xff\xff\xff\xffWAVEfmt \x10\x00\x00\x00" + b"\x00" * 20
+ b"data\xff\xff\xff\xff" + b"\x11\x22" * 64
)
# A second span's WAV with distinct PCM — its header is stripped when stitched after span 0.
_WAV2 = (
b"RIFF\xff\xff\xff\xffWAVEfmt \x10\x00\x00\x00" + b"\x00" * 20
+ b"data\xff\xff\xff\xff" + b"\x33\x44" * 32
)
_PCM2 = b"\x33\x44" * 32 # the part of _WAV2 after `data`+size (what stitching keeps)
async def _drain(gen) -> bytes:
@@ -34,6 +40,12 @@ async def _drain(gen) -> bytes:
return out
def _json_voice(route, i: int) -> str:
import json as _json
return _json.loads(route.calls[i].request.content)["voice"]
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."""
@@ -73,12 +85,15 @@ class TestGatewayBody:
assert dead not in b
class TestTtsStream:
class TestTtsStreamStitched:
@respx.mock
async def test_streams_chunks_and_posts_openai_body(self) -> None:
async def test_single_span_verbatim_and_posts_openai_body(self) -> None:
# A single-span list is a verbatim passthrough (INV-TTS-6) with the OpenAI body.
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))
out = await _drain(
tts_stream_stitched([("donut", "hello there")], client=client, url=_URL)
)
assert out == _WAV # passed through verbatim — no header rewrite
import json as _json
@@ -89,12 +104,39 @@ class TestTtsStream:
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 def test_two_spans_stitched_one_header(self) -> None:
# Span 0 verbatim (its WAV header + PCM), span 1 header-STRIPPED → one continuous
# stream with exactly one leading header (INV-TTS-7). Distinct voices per span.
route = respx.post(_URL).mock(
side_effect=[httpx.Response(200, content=_WAV), httpx.Response(200, content=_WAV2)]
)
async with httpx.AsyncClient() as client:
await _drain(tts_stream("hi", voice="donut", client=client))
out = await _drain(
tts_stream_stitched(
[("miranda", "spoken bit"), ("emmie", "narrated bit")],
client=client, url=_URL,
)
)
assert out == _WAV + _PCM2 # span1's header dropped, PCM kept
assert out.count(b"RIFF") == 1 # exactly one WAV header
assert _json_voice(route, 0) == "miranda" and _json_voice(route, 1) == "emmie"
@respx.mock
async def test_empty_span_skipped(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_stitched(
[("miranda", " "), ("donut", "real")], client=client, url=_URL
)
)
assert out == _WAV and len(route.calls) == 1 # blank span never synthesized
@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_stitched([("donut", "hi")], client=client))
assert route.called # the module default points at the dots-tts gateway
@respx.mock
@@ -102,7 +144,7 @@ class TestTtsStream:
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))
await _drain(tts_stream_stitched([("glados", "hi")], client=client, url=_URL))
assert exc.value.status == 500
@respx.mock
@@ -110,16 +152,27 @@ class TestTtsStream:
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))
await _drain(tts_stream_stitched([("glados", "hi")], 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))
# (return what streamed), never raise — the pivot is yielded_any. 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_stitched([("donut", "hi")], client=client, url=_URL))
assert out == _WAV # head kept, no raise
@respx.mock
async def test_later_span_open_fail_after_commit_degrades(self) -> None:
# Span 0 commits a 200 + bytes; span 1's OPEN then 500s. Because the stream is already
# committed, this DEGRADES (keep span 0), never raises into the 200 (INV-TTS-4).
route = respx.post(_URL).mock(
side_effect=[httpx.Response(200, content=_WAV), httpx.Response(500, content=b"boom")]
)
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
out = await _drain(
tts_stream_stitched([("miranda", "a"), ("emmie", "b")], client=client, url=_URL)
)
assert out == _WAV and len(route.calls) == 2 # span0 kept, span1 attempted then dropped