mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
bc4dcb1b02
Salvaged from PR #47588 and rebased onto the post-campaign streaming core: the StreamingTTSProvider ABC/registry and the ElevenLabs/OpenAI streamers already live on main (tools/tts_streaming.py), so this ports the pieces main lacked: - GeminiStreamer: streamGenerateContent?alt=sse -> base64 PCM chunks (24 kHz mono int16), reusing main's DEFAULT_GEMINI_TTS_* constants. - XAIStreamer: WebSocket wss://api.x.ai/v1/tts -> binary PCM frames, async->sync bridged via the _collect_async test seam. - tts.streaming.provider config knob: pin one streamer, or 'auto' to walk the priority list elevenlabs -> gemini -> openai -> xai. Unset keeps the never-swap-the-user's-voice default. - docs/streaming-tts.md: architecture, capability matrix, how to add a provider. - Unit tests for the knob, SSE parsing, and the WS bridge; key-gated E2E tests (skipped without credentials). Refs: #47588
109 lines
3.4 KiB
Python
109 lines
3.4 KiB
Python
"""End-to-end tests for streaming TTS providers. Gated on real API keys.
|
|
|
|
Salvaged from PR #47588 (@Cdddo) and adapted to the current provider ABC
|
|
(``StreamingTTSProvider(tts_config, section)``). These tests are SKIPPED by
|
|
default — they only run when the relevant credential is present. They're
|
|
useful for catching provider-API drift and verifying the integration
|
|
end-to-end, but they shouldn't run in CI without secrets configured.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
|
|
import pytest
|
|
|
|
|
|
def _has_xai_creds() -> bool:
|
|
# Plain os.environ, matching the other gates here: the repo's test
|
|
# conftest scrubs dotenv/pooled secrets, so gating on the richer
|
|
# resolver would collect a test whose runtime credentials are gone.
|
|
return bool(os.environ.get("XAI_API_KEY"))
|
|
|
|
|
|
# --- ElevenLabs ---
|
|
|
|
|
|
@pytest.mark.skipif(
|
|
not os.environ.get("ELEVENLABS_API_KEY"),
|
|
reason="ELEVENLABS_API_KEY not set",
|
|
)
|
|
def test_elevenlabs_streaming_real():
|
|
"""Generate audio from the real ElevenLabs API and verify non-empty chunks."""
|
|
from tools.tts_streaming import ElevenLabsStreamer
|
|
|
|
provider = ElevenLabsStreamer({}, {})
|
|
chunks = list(provider.stream("Hello world, this is a test."))
|
|
assert len(chunks) > 0
|
|
total_bytes = sum(len(c) for c in chunks)
|
|
# 1s of PCM at 24kHz mono int16 = 48000 bytes; expect at least 1k for real audio
|
|
assert total_bytes > 1000
|
|
|
|
|
|
# --- Gemini ---
|
|
|
|
|
|
@pytest.mark.skipif(
|
|
not (os.environ.get("GEMINI_API_KEY") or os.environ.get("GOOGLE_API_KEY")),
|
|
reason="GEMINI_API_KEY/GOOGLE_API_KEY not set",
|
|
)
|
|
def test_gemini_streaming_real():
|
|
"""Generate audio from the real Gemini SSE API and verify non-empty chunks."""
|
|
from tools.tts_streaming import GeminiStreamer
|
|
|
|
provider = GeminiStreamer({}, {})
|
|
chunks = list(provider.stream("Hola, esto es una prueba."))
|
|
assert len(chunks) > 0
|
|
total_bytes = sum(len(c) for c in chunks)
|
|
assert total_bytes > 1000
|
|
|
|
|
|
# --- OpenAI ---
|
|
|
|
|
|
@pytest.mark.skipif(
|
|
not os.environ.get("OPENAI_API_KEY"),
|
|
reason="OPENAI_API_KEY not set",
|
|
)
|
|
def test_openai_streaming_real():
|
|
"""Generate audio from the real OpenAI API and verify non-empty chunks."""
|
|
from tools.tts_streaming import OpenAIStreamer
|
|
|
|
provider = OpenAIStreamer({}, {})
|
|
chunks = list(provider.stream("Hello, this is a test."))
|
|
assert len(chunks) > 0
|
|
total_bytes = sum(len(c) for c in chunks)
|
|
assert total_bytes > 1000
|
|
|
|
|
|
# --- xAI ---
|
|
|
|
|
|
@pytest.mark.skipif(not _has_xai_creds(), reason="no xAI credentials")
|
|
def test_xai_streaming_real():
|
|
"""Generate audio from the real xAI WebSocket API and verify non-empty frames."""
|
|
from tools.tts_streaming import XAIStreamer
|
|
|
|
provider = XAIStreamer({}, {})
|
|
chunks = list(provider.stream("Hello, this is a test."))
|
|
assert len(chunks) > 0
|
|
total_bytes = sum(len(c) for c in chunks)
|
|
assert total_bytes > 1000
|
|
|
|
|
|
# --- Resolver integration (no network; requires at least one key) ---
|
|
|
|
|
|
@pytest.mark.skipif(
|
|
not (
|
|
os.environ.get("ELEVENLABS_API_KEY")
|
|
or os.environ.get("GEMINI_API_KEY")
|
|
or os.environ.get("GOOGLE_API_KEY")
|
|
or os.environ.get("OPENAI_API_KEY")
|
|
),
|
|
reason="no streaming-capable TTS key set",
|
|
)
|
|
def test_auto_resolver_finds_a_real_provider():
|
|
from tools.tts_streaming import StreamingTTSProvider, resolve_streaming_provider
|
|
|
|
provider = resolve_streaming_provider({"streaming": {"provider": "auto"}})
|
|
assert isinstance(provider, StreamingTTSProvider)
|