Make speech streaming default to SSE (#4679)

Signed-off-by: syd520zy <529477025@qq.com>

examples/online_serving/text_to_speech/README.md

@@ -79,7 +79,7 @@ response = client.audio.speech.create(
 response.stream_to_file("output.wav")
 ```
 
-Streaming PCM output (where supported) — set `stream=true` with `response_format="pcm"`:
+Streaming PCM output (where supported) — set `stream=true`, `stream_format="audio"`, and `response_format="pcm"`:
 
 ```bash
 curl -X POST http://localhost:8091/v1/audio/speech \
@@ -88,6 +88,7 @@ curl -X POST http://localhost:8091/v1/audio/speech \
         "input": "Hello, how are you?",
         "voice": "default",
         "stream": true,
+        "stream_format": "audio",
         "response_format": "pcm"
     }' --no-buffer | play -t raw -r 24000 -e signed -b 16 -c 1 -
 ```
@@ -363,6 +364,7 @@ curl -X POST http://localhost:8091/v1/audio/speech \
         \"input\": \"Hello, streaming output from MOSS-TTS-Nano.\",
         \"ref_audio\": \"data:audio/wav;base64,${REF_AUDIO}\",
         \"stream\": true,
+        \"stream_format\": \"audio\",
         \"response_format\": \"pcm\"
     }" --no-buffer | play -t raw -r 48000 -e signed -b 16 -c 1 -
 ```
@@ -528,10 +530,11 @@ curl -X POST http://localhost:8091/v1/audio/speech \
         "voice": "vivian",
         "language": "English",
         "stream": true,
+        "stream_format": "audio",
         "response_format": "pcm"
     }' --no-buffer | play -t raw -r 24000 -e signed -b 16 -c 1 -
 ```
-Streaming requires `response_format="pcm"` and `async_chunk: true` on the stage config (default in `qwen3_tts.yaml`). `speed` is not supported when streaming.
+Raw PCM streaming requires `stream_format="audio"`, `response_format="pcm"`, and `async_chunk: true` on the stage config (default in `qwen3_tts.yaml`). `speed` is not supported when streaming.
 
 ### Streaming WebSocket
 The `/v1/audio/speech/stream` endpoint accepts text incrementally, splits it at sentence boundaries, and emits one PCM stream per sentence:
@@ -632,7 +635,7 @@ After startup, `/v1/audio/voices` lists `alice`, and `/v1/audio/speech` can use
 ```bash
 python voxcpm2/gradio_demo.py
 ```
-Uses an AudioWorklet-based player adapted from the Qwen3-TTS demo for gap-free playback. Audio is streamed from the OpenAI Speech endpoint with `stream=true`.
+Uses an AudioWorklet-based player adapted from the Qwen3-TTS demo for gap-free playback. Raw PCM audio is streamed from the OpenAI Speech endpoint with `stream=true` and `stream_format="audio"`.
 
 ---
 

examples/online_serving/text_to_speech/cosyvoice3/speech_client.py

@@ -60,6 +60,7 @@ def run_tts(args) -> None:
 
     if args.stream:
         payload["stream"] = True
+        payload["stream_format"] = "audio"
         payload["response_format"] = "pcm"
 
     print(f"Model: {args.model}")

examples/online_serving/text_to_speech/fish_speech/gradio_demo.py

@@ -66,6 +66,8 @@ def build_payload(
         "response_format": "pcm" if stream else response_format,
         "stream": stream,
     }
+    if stream:
+        payload["stream_format"] = "audio"
 
     # Voice cloning: ref_audio takes priority over URL.
     ref_url_stripped = ref_audio_url.strip() if ref_audio_url else ""

examples/online_serving/text_to_speech/fish_speech/speech_client.py

@@ -53,6 +53,7 @@ def run_tts(args) -> None:
 
     if args.stream:
         payload["stream"] = True
+        payload["stream_format"] = "audio"
         payload["response_format"] = "pcm"
 
     print(f"Model: {args.model}")

examples/online_serving/text_to_speech/glm_tts/gradio_demo.py

@@ -64,6 +64,8 @@ def build_payload(
         "stream": stream,
         "max_new_tokens": max_new_tokens,
     }
+    if stream:
+        payload["stream_format"] = "audio"
 
     # Voice cloning: ref_audio takes priority over URL.
     ref_url_stripped = ref_audio_url.strip() if ref_audio_url else ""

examples/online_serving/text_to_speech/glm_tts/openai_speech_client.py

@@ -40,6 +40,9 @@ def run_tts_generation(args) -> None:
         "ref_audio": args.ref_audio,
         "ref_text": args.ref_text,
     }
+    if args.stream:
+        payload["stream_format"] = "audio"
+        payload["response_format"] = "pcm"
     if args.max_new_tokens:
         payload["max_new_tokens"] = args.max_new_tokens
 

examples/online_serving/text_to_speech/ming_tts/openai_speech_client.py

@@ -123,6 +123,7 @@ def run_tts(args) -> None:
         payload["max_new_tokens"] = args.max_new_tokens
     if args.stream:
         payload["stream"] = True
+        payload["stream_format"] = "audio"
         payload["response_format"] = "pcm"
 
     api_url = f"{args.api_base}/v1/audio/speech"

examples/online_serving/text_to_speech/ming_tts/run_curl.sh

@@ -65,6 +65,7 @@ PY
             \"model\": \"${MODEL}\",
             \"input\": \"${TEXT}\",
             \"stream\": true,
+            \"stream_format\": \"audio\",
             \"response_format\": \"pcm\"
         }" "$STREAM_OUTPUT"
         ;;

examples/online_serving/text_to_speech/moss_tts_nano/gradio_demo.py

@@ -335,6 +335,7 @@ def build_payload(
         "ref_audio": encode_audio_to_base64(ref_audio),
         "response_format": "pcm" if stream else response_format,
         "stream": stream,
+        **({"stream_format": "audio"} if stream else {}),
     }
 
 

examples/online_serving/text_to_speech/qwen3_tts/tts_common.py

@@ -93,6 +93,8 @@ def build_payload(
         "response_format": "pcm" if stream else response_format,
         "stream": stream,
     }
+    if stream:
+        payload["stream_format"] = "audio"
     if not stream:
         payload["speed"] = speed
 

examples/online_serving/text_to_speech/voxcpm2/gradio_demo.py

@@ -515,6 +515,8 @@ def create_app(api_base: str):
                 "response_format": "pcm" if stream_enabled else "wav",
                 "stream": stream_enabled,
             }
+            if stream_enabled:
+                payload["stream_format"] = "audio"
 
             # Reference audio for cloning
             ref_url_s = ref_url.strip() if ref_url else ""