Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

fix(server): return plain text for response_format=text

David-Wu111932c9ebb05932
diff --git a/funasr/bin/_server_app.py b/funasr/bin/_server_app.py
index 588f1fbb1..8822e94a4 100644
--- a/funasr/bin/_server_app.py
+++ b/funasr/bin/_server_app.py
@@ -20,7 +20,7 @@ import soundfile as sf
try:
from fastapi import FastAPI, UploadFile, File, Form, HTTPException
from fastapi.middleware.cors import CORSMiddleware
- from fastapi.responses import JSONResponse
+ from fastapi.responses import JSONResponse, PlainTextResponse
except ImportError:
raise ImportError(
"funasr-server requires additional packages. Install with: pip install vllm fastapi uvicorn python-multipart"
@@ -529,7 +529,7 @@ def create_app(
if response_format == "verbose_json":
return JSONResponse(build_openai_verbose_json(result, requested_language=language))
elif response_format == "text":
- return JSONResponse(result["text"])
+ return PlainTextResponse(result["text"])
else:
return JSONResponse({"text": result["text"]})
diff --git a/tests/test_server_app_openai_segments.py b/tests/test_server_app_openai_segments.py
index 06a4951f8..28df9bc6e 100644
--- a/tests/test_server_app_openai_segments.py
+++ b/tests/test_server_app_openai_segments.py
@@ -12,6 +12,11 @@ SERVICE_PATH = REPO_ROOT / "funasr" / "bin" / "_server_app.py"
SERVER_CLI_PATH = REPO_ROOT / "funasr" / "bin" / "server.py"
+class PlainTextResponseStub:
+ def __init__(self, content=None):
+ self.content = content
+
+
def load_server_app(monkeypatch):
class DummyFastAPI:
def __init__(self, *args, **kwargs):
@@ -57,6 +62,7 @@ def load_server_app(monkeypatch):
responses_stub = types.ModuleType("fastapi.responses")
responses_stub.JSONResponse = lambda content=None: content
+ responses_stub.PlainTextResponse = PlainTextResponseStub
monkeypatch.setitem(sys.modules, "fastapi", fastapi_stub)
monkeypatch.setitem(sys.modules, "fastapi.middleware", middleware_stub)
@@ -260,6 +266,28 @@ def test_n8n_whisper_model_alias_uses_preloaded_model(monkeypatch):
]
+def test_text_response_format_returns_plain_text(monkeypatch):
+ module = load_server_app(monkeypatch)
+ install_dummy_funasr(monkeypatch, generated_text='say "hi"')
+ monkeypatch.setattr(module.sf, "info", lambda path: types.SimpleNamespace(duration=1.25))
+ app = module.create_app(device="cpu", preload_model="sensevoice")
+ transcribe = app.routes[("POST", "/v1/audio/transcriptions")]
+
+ response = asyncio.run(
+ transcribe(
+ file=DummyUpload(),
+ model="sensevoice",
+ language=None,
+ response_format="text",
+ spk=False,
+ )
+ )
+
+ # OpenAI returns the bare transcript, not a JSON-encoded string.
+ assert isinstance(response, PlainTextResponseStub)
+ assert response.content == 'say "hi"'
+
+
def test_openai_verbose_json_preserves_speaker_labels(monkeypatch):
module = load_server_app(monkeypatch)