mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(tts): add speed support for Edge TTS and OpenAI TTS

Browse source 
Read tts.speed (global) or tts.<provider>.speed (provider-specific) from
config. Provider-specific takes precedence over global.

- Edge TTS: converts speed float to SSML prosody rate string
- OpenAI TTS: passes speed param clamped to 0.25-4.0
- MiniMax: wired into global tts.speed fallback for consistency

Co-authored-by: 0xbyt4 <0xbyt4@users.noreply.github.com>
This commit is contained in:
0xbyt4 2026-04-12 16:44:24 -07:00 • committed by Teknium
parent 651419b014
commit 8ec0656f53
1 changed files with 13 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

16
tools/tts_tool.py
View file

@ -188,8 +188,14 @@ async def _generate_edge_tts(text: str, output_path: str, tts_config: Dict[str,
_edge_tts = _import_edge_tts()
edge_config = tts_config.get("edge", {})
voice = edge_config.get("voice", DEFAULT_EDGE_VOICE)
speed = float(edge_config.get("speed", tts_config.get("speed", 1.0)))
communicate = _edge_tts.Communicate(text, voice)
kwargs = {"voice": voice}
if speed != 1.0:
pct = round((speed - 1.0) * 100)
kwargs["rate"] = f"{pct:+d}%"
communicate = _edge_tts.Communicate(text, **kwargs)
await communicate.save(output_path)
return output_path
@ -261,6 +267,7 @@ def _generate_openai_tts(text: str, output_path: str, tts_config: Dict[str, Any]
model = oai_config.get("model", DEFAULT_OPENAI_MODEL)
voice = oai_config.get("voice", DEFAULT_OPENAI_VOICE)
base_url = oai_config.get("base_url", base_url)
speed = float(oai_config.get("speed", tts_config.get("speed", 1.0)))
# Determine response format from extension
if output_path.endswith(".ogg"):
@ -271,13 +278,16 @@ def _generate_openai_tts(text: str, output_path: str, tts_config: Dict[str, Any]
OpenAIClient = _import_openai_client()
client = OpenAIClient(api_key=api_key, base_url=base_url)
try:
response = client.audio.speech.create(
create_kwargs = dict(
model=model,
voice=voice,
input=text,
response_format=response_format,
extra_headers={"x-idempotency-key": str(uuid.uuid4())},
)
if speed != 1.0:
create_kwargs["speed"] = max(0.25, min(4.0, speed))
response = client.audio.speech.create(**create_kwargs)
response.stream_to_file(output_path)
return output_path
@ -314,7 +324,7 @@ def _generate_minimax_tts(text: str, output_path: str, tts_config: Dict[str, Any
mm_config = tts_config.get("minimax", {})
model = mm_config.get("model", DEFAULT_MINIMAX_MODEL)
voice_id = mm_config.get("voice_id", DEFAULT_MINIMAX_VOICE_ID)
speed = mm_config.get("speed", 1)
speed = mm_config.get("speed", tts_config.get("speed", 1))
vol = mm_config.get("vol", 1)
pitch = mm_config.get("pitch", 0)
base_url = mm_config.get("base_url", DEFAULT_MINIMAX_BASE_URL)