Skip to content

Class swarmauri_standard.tts.PlayhtTTS.PlayhtTTS

swarmauri_standard.tts.PlayhtTTS.PlayhtTTS

PlayhtTTS(**data)

Bases: TTSBase

A class for Play.ht text-to-speech (TTS) synthesis using various voice models.

This class interacts with the Play.ht API to synthesize text to speech, clone voices, and manage voice operations (like getting, cloning, and deleting). Attributes: allowed_models (List[str]): List of TTS models supported by Play.ht, such as "Play3.0-mini" and "PlayHT2.0". allowed_voices (List[str]): List of voice names available for the selected model. voice (str): The selected voice name for synthesis (default: "Adolfo"). api_key (str): API key for authenticating with Play.ht's API. user_id (str): User ID for authenticating with Play.ht's API. name (str): Name of the TTS model to use (default: "Play3.0-mini"). type (Literal["PlayhtTTS"]): Fixed type attribute to indicate this is a "PlayhtTTS". output_format (str): Format of the output audio file, e.g., "mp3".

Provider resourses: https://docs.play.ht/reference/api-getting-started

Initialize the PlayhtTTS with API credentials and voice settings.

Source code in swarmauri_standard/tts/PlayhtTTS.py
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
def __init__(self, **data) -> None:
    """
    Initialize the PlayhtTTS with API credentials and voice settings.
    """
    super().__init__(**data)
    self._headers = {
        "accept": "audio/mpeg",
        "content-type": "application/json",
        "AUTHORIZATION": self.api_key.get_secret_value(),
        "X-USER-ID": self.user_id,
    }
    self.allowed_models = self.allowed_models or self.get_allowed_models()
    self.name = self.allowed_models[0]
    self.__prebuilt_voices = self._fetch_prebuilt_voices()
    self.allowed_voices = self._get_allowed_voices(self.name)
    self._validate_voice_in_allowed_voices()

voice class-attribute instance-attribute

voice = Field(default='Adolfo')

api_key instance-attribute

api_key

user_id instance-attribute

user_id

type class-attribute instance-attribute

type = 'PlayhtTTS'

output_format class-attribute instance-attribute

output_format = 'mp3'

allowed_models class-attribute instance-attribute

allowed_models = allowed_models or get_allowed_models()

name class-attribute instance-attribute

name = allowed_models[0]

allowed_voices class-attribute instance-attribute

allowed_voices = _get_allowed_voices(name)

model_config class-attribute instance-attribute

model_config = ConfigDict(
    extra="forbid", arbitrary_types_allowed=True
)

id class-attribute instance-attribute

id = Field(default_factory=generate_id)

members class-attribute instance-attribute

members = None

owners class-attribute instance-attribute

owners = None

host class-attribute instance-attribute

host = None

default_logger class-attribute

default_logger = None

logger class-attribute instance-attribute

logger = None

resource class-attribute instance-attribute

resource = Field(default=TTS.value, frozen=True)

version class-attribute instance-attribute

version = '0.1.0'

predict

predict(text, audio_path='output.mp3')

Convert text to speech using Play.ht's API and save as an audio file.

PARAMETER DESCRIPTION
text

The text to convert to speech.

TYPE: str

audio_path

Path to save the synthesized audio.

TYPE: str DEFAULT: 'output.mp3'

Returns: str: Absolute path to the saved audio file.

Source code in swarmauri_standard/tts/PlayhtTTS.py
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
@retry_on_status_codes((429, 529), max_retries=1)
def predict(self, text: str, audio_path: str = "output.mp3") -> str:
    """
    Convert text to speech using Play.ht's API and save as an audio file.

    Parameters:
        text (str): The text to convert to speech.
        audio_path (str): Path to save the synthesized audio.
    Returns:
        str: Absolute path to the saved audio file.
    """
    payload = {
        "voice": self._get_voice_id(self.voice),
        "output_format": self.output_format,
        "voice_engine": self.name,
        "text": text,
    }

    try:
        with httpx.Client(base_url=self._BASE_URL, timeout=30) as self._client:
            response = self._client.post(
                "/tts/stream", json=payload, headers=self._headers
            )
            response.raise_for_status()

        with open(audio_path, "wb") as f:
            f.write(response.content)

        return os.path.abspath(audio_path)
    except Exception as e:
        raise RuntimeError(f"Text-to-Speech synthesis failed: {e}")

apredict async

apredict(text, audio_path='output.mp3')

Asynchronously convert text to speech and save it as an audio file.

PARAMETER DESCRIPTION
text

Text to convert to speech.

TYPE: str

audio_path

Path to save the synthesized audio file.

TYPE: str DEFAULT: 'output.mp3'

RETURNS DESCRIPTION
str

Path to the saved audio file.

TYPE: str

Source code in swarmauri_standard/tts/PlayhtTTS.py
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
@retry_on_status_codes((429, 529), max_retries=1)
async def apredict(self, text: str, audio_path: str = "output.mp3") -> str:
    """
    Asynchronously convert text to speech and save it as an audio file.

    Parameters:
        text (str): Text to convert to speech.
        audio_path (str): Path to save the synthesized audio file.

    Returns:
        str: Path to the saved audio file.
    """
    payload = {
        "voice": self._get_voice_id(self.voice),
        "output_format": self.output_format,
        "voice_engine": self.name,
        "text": text,
    }

    try:
        async with httpx.AsyncClient(
            base_url=self._BASE_URL, timeout=30
        ) as async_client:
            response = await async_client.post(
                "/tts/stream", json=payload, headers=self._headers
            )
            response.raise_for_status()
        with open(audio_path, "wb") as f:
            f.write(response.content)
        return os.path.abspath(audio_path)
    except Exception as e:
        raise RuntimeError(f"Text-to-Speech synthesis failed: {e}")

batch

batch(text_path_dict)

Process multiple text-to-speech conversions synchronously.

PARAMETER DESCRIPTION
text_path_dict

Dictionary of text and corresponding audio paths.

TYPE: Dict[str, str]

Returns: List: List of audio file paths.

Source code in swarmauri_standard/tts/PlayhtTTS.py
220
221
222
223
224
225
226
227
228
229
def batch(self, text_path_dict: Dict[str, str]) -> List:
    """
    Process multiple text-to-speech conversions synchronously.

    Parameters:
        text_path_dict (Dict[str, str]): Dictionary of text and corresponding audio paths.
    Returns:
        List: List of audio file paths.
    """
    return [self.predict(text, path) for text, path in text_path_dict.items()]

abatch async

abatch(text_path_dict, max_concurrent=5)

Process multiple text-to-speech conversions asynchronously with controlled concurrency.

PARAMETER DESCRIPTION
text_path_dict

Dictionary of text and corresponding audio paths.

TYPE: Dict[str, str]

max_concurrent

Maximum number of concurrent tasks.

TYPE: int DEFAULT: 5

Returns: List: List of audio file paths.

Source code in swarmauri_standard/tts/PlayhtTTS.py
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
async def abatch(
    self, text_path_dict: Dict[str, str], max_concurrent: int = 5
) -> List["str"]:
    """
    Process multiple text-to-speech conversions asynchronously with controlled concurrency.

    Parameters:
        text_path_dict (Dict[str, str]): Dictionary of text and corresponding audio paths.
        max_concurrent (int): Maximum number of concurrent tasks.
    Returns:
        List: List of audio file paths.
    """
    semaphore = asyncio.Semaphore(max_concurrent)

    async def process_text(text, path) -> str:
        async with semaphore:
            return await self.apredict(text, path)

    tasks = [process_text(text, path) for text, path in text_path_dict.items()]
    return await asyncio.gather(*tasks)

clone_voice_from_file

clone_voice_from_file(voice_name, sample_file_path)

Clone a voice using an audio file.

PARAMETER DESCRIPTION
voice_name

The name for the cloned voice.

TYPE: str

sample_file_path

Path to the sample audio file.

TYPE: str

RETURNS DESCRIPTION
dict

Response from the Play.ht API.

TYPE: dict

Source code in swarmauri_standard/tts/PlayhtTTS.py
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
def clone_voice_from_file(self, voice_name: str, sample_file_path: str) -> dict:
    """
    Clone a voice using an audio file.

    Parameters:
        voice_name (str): The name for the cloned voice.
        sample_file_path (str): Path to the sample audio file.

    Returns:
        dict: Response from the Play.ht API.
    """
    files = {
        "sample_file": (
            sample_file_path.split("/")[-1],
            open(sample_file_path, "rb"),
            "audio/mp4",
        )
    }
    payload = {"voice_name": voice_name}
    self._headers["accept"] = "application/json"

    try:
        with httpx.Client(base_url=self._BASE_URL) as client:
            response = client.post(
                "/cloned-voices/instant",
                data=payload,
                files=files,
                headers=self._headers,
            )
            response.raise_for_status()

        return response.json()
    except httpx.RequestError as e:
        print(f"An error occurred while cloning the voice: {e}")
        return {"error": str(e)}

clone_voice_from_url

clone_voice_from_url(voice_name, sample_file_url)

Clone a voice by sending a URL to an audio file to Play.ht API.

:param voice_name: The name for the cloned voice. :param sample_file_url: The URL to the audio file to be used for cloning the voice. :return: A dictionary containing the response from the Play.ht API.

Source code in swarmauri_standard/tts/PlayhtTTS.py
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
def clone_voice_from_url(self, voice_name: str, sample_file_url: str) -> dict:
    """
    Clone a voice by sending a URL to an audio file to Play.ht API.

    :param voice_name: The name for the cloned voice.
    :param sample_file_url: The URL to the audio file to be used for cloning the voice.
    :return: A dictionary containing the response from the Play.ht API.
    """
    # Constructing the payload with the sample file URL
    payload = (
        f'-----011000010111000001101001\r\nContent-Disposition: form-data; name="sample_file_url"\r\n\r\n\
        {sample_file_url}\r\n-----011000010111000001101001--; name="voice_name"\r\n\r\n\
        {voice_name}\r\n-----011000010111000001101001--'
    )

    self._headers["content-type"] = (
        "multipart/form-data; boundary=---011000010111000001101001"
    )
    self._headers["accept"] = "application/json"

    try:
        with httpx.Client(base_url=self._BASE_URL) as client:
            response = client.post(
                "/cloned-voices/instant", data=payload, headers=self._headers
            )
            response.raise_for_status()

        return response.json()

    except httpx.RequestError as e:
        print(f"An error occurred while cloning the voice: {e}")
        return {"error": str(e)}

delete_cloned_voice

delete_cloned_voice(voice_id)

Delete a cloned voice using its voice_id from Play.ht.

:param voice_id: The ID of the cloned voice to delete. :return: A dictionary containing the response from the Play.ht API.

Source code in swarmauri_standard/tts/PlayhtTTS.py
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
def delete_cloned_voice(self, voice_id: str) -> dict:
    """
    Delete a cloned voice using its voice_id from Play.ht.

    :param voice_id: The ID of the cloned voice to delete.
    :return: A dictionary containing the response from the Play.ht API.
    """

    payload = {"voice_id": voice_id}
    self._headers["accept"] = "application/json"

    try:
        with httpx.Client(base_url=self._BASE_URL) as client:
            response = client.delete(
                "/cloned-voices", json=payload, headers=self._headers
            )
            response.raise_for_status()

        return response.json()

    except httpx.RequestError as e:
        print(f"An error occurred while deleting the cloned voice: {e}")
        return {"error": str(e)}

get_cloned_voices

get_cloned_voices()

Get a list of cloned voices from Play.ht.

:return: A dictionary containing the cloned voices or an error message.

Source code in swarmauri_standard/tts/PlayhtTTS.py
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
def get_cloned_voices(self) -> dict:
    """
    Get a list of cloned voices from Play.ht.

    :return: A dictionary containing the cloned voices or an error message.
    """
    self._headers["accept"] = "application/json"

    try:
        with httpx.Client(base_url=self._BASE_URL) as client:
            response = client.get("/cloned-voices", headers=self._headers)
            response.raise_for_status()

        return response.json()

    except httpx.RequestError as e:
        print(f"An error occurred while retrieving cloned voices: {e}")
        return {"error": str(e)}

get_allowed_models

get_allowed_models()

Queries the LLMProvider API endpoint to retrieve the list of allowed models.

RETURNS DESCRIPTION
List[str]

List[str]: List of allowed model names.

Source code in swarmauri_standard/tts/PlayhtTTS.py
364
365
366
367
368
369
370
371
372
def get_allowed_models(self) -> List[str]:
    """
    Queries the LLMProvider API endpoint to retrieve the list of allowed models.

    Returns:
        List[str]: List of allowed model names.
    """
    models_data = ["Play3.0-mini", "PlayHT2.0-turbo", "PlayHT1.0", "PlayHT2.0"]
    return models_data

stream

stream(text)

Stream TTS audio using httpx.

PARAMETER DESCRIPTION
text

The text to convert to speech.

TYPE: str

RETURNS DESCRIPTION
bytes

bytes of the audio.

TYPE: bytes

Source code in swarmauri_standard/tts/PlayhtTTS.py
374
375
376
377
378
379
380
381
382
383
384
def stream(self, text: str) -> bytes:
    """
    Stream TTS audio using httpx.

    Parameters:
        text (str): The text to convert to speech.

    Returns:
        bytes: bytes of the audio.
    """
    raise NotImplementedError("Stream method not implemented for PlayhtTTS")

astream async

astream(text)

Asynchronously stream TTS audio using httpx.

PARAMETER DESCRIPTION
text

The text to convert to speech.

TYPE: str

RETURNS DESCRIPTION
bytes

bytes of the audio.

TYPE: bytes

Source code in swarmauri_standard/tts/PlayhtTTS.py
386
387
388
389
390
391
392
393
394
395
396
async def astream(self, text: str) -> bytes:
    """
    Asynchronously stream TTS audio using httpx.

    Parameters:
        text (str): The text to convert to speech.

    Returns:
        bytes: bytes of the audio.
    """
    raise NotImplementedError("AStream method not implemented for PlayhtTTS")

register_model classmethod

register_model()

Decorator to register a base model in the unified registry.

RETURNS DESCRIPTION
Callable

A decorator function that registers the model class.

TYPE: Callable[[Type[BaseModel]], Type[BaseModel]]

Source code in swarmauri_base/DynamicBase.py
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
@classmethod
def register_model(cls) -> Callable[[Type[BaseModel]], Type[BaseModel]]:
    """
    Decorator to register a base model in the unified registry.

    Returns:
        Callable: A decorator function that registers the model class.
    """

    def decorator(model_cls: Type[BaseModel]):
        """Register ``model_cls`` as a base model."""
        model_name = model_cls.__name__
        if model_name in cls._registry:
            glogger.warning(
                "Model '%s' is already registered; skipping duplicate.", model_name
            )
            return model_cls

        cls._registry[model_name] = {"model_cls": model_cls, "subtypes": {}}
        glogger.debug("Registered base model '%s'.", model_name)
        DynamicBase._recreate_models()
        return model_cls

    return decorator

register_type classmethod

register_type(resource_type=None, type_name=None)

Decorator to register a subtype under one or more base models in the unified registry.

PARAMETER DESCRIPTION
resource_type

The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase) are used.

TYPE: Optional[Union[Type[T], List[Type[T]]]] DEFAULT: None

type_name

An optional custom type name for the subtype.

TYPE: Optional[str] DEFAULT: None

RETURNS DESCRIPTION
Callable

A decorator function that registers the subtype.

TYPE: Callable[[Type[DynamicBase]], Type[DynamicBase]]

Source code in swarmauri_base/DynamicBase.py
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
@classmethod
def register_type(
    cls,
    resource_type: Optional[Union[Type[T], List[Type[T]]]] = None,
    type_name: Optional[str] = None,
) -> Callable[[Type["DynamicBase"]], Type["DynamicBase"]]:
    """
    Decorator to register a subtype under one or more base models in the unified registry.

    Parameters:
        resource_type (Optional[Union[Type[T], List[Type[T]]]]):
            The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase)
            are used.
        type_name (Optional[str]): An optional custom type name for the subtype.

    Returns:
        Callable: A decorator function that registers the subtype.
    """

    def decorator(subclass: Type["DynamicBase"]):
        """Register ``subclass`` as a subtype."""
        if resource_type is None:
            resource_types = [
                base for base in subclass.__bases__ if base is not cls
            ]
        elif not isinstance(resource_type, list):
            resource_types = [resource_type]
        else:
            resource_types = resource_type

        for rt in resource_types:
            if not issubclass(subclass, rt):
                raise TypeError(
                    f"'{subclass.__name__}' must be a subclass of '{rt.__name__}'."
                )
            final_type_name = type_name or getattr(
                subclass, "_type", subclass.__name__
            )
            base_model_name = rt.__name__

            if base_model_name not in cls._registry:
                cls._registry[base_model_name] = {"model_cls": rt, "subtypes": {}}
                glogger.debug(
                    "Created new registry entry for base model '%s'.",
                    base_model_name,
                )

            subtypes_dict = cls._registry[base_model_name]["subtypes"]
            if final_type_name in subtypes_dict:
                glogger.warning(
                    "Type '%s' already exists under '%s'; skipping duplicate.",
                    final_type_name,
                    base_model_name,
                )
                continue

            subtypes_dict[final_type_name] = subclass
            glogger.debug(
                "Registered '%s' as '%s' under '%s'.",
                subclass.__name__,
                final_type_name,
                base_model_name,
            )

        DynamicBase._recreate_models()
        return subclass

    return decorator

model_validate_toml classmethod

model_validate_toml(toml_data)

Validate a model from a TOML string.

Source code in swarmauri_base/TomlMixin.py
12
13
14
15
16
17
18
19
20
21
22
23
24
@classmethod
def model_validate_toml(cls, toml_data: str):
    """Validate a model from a TOML string."""
    try:
        # Parse TOML into a Python dictionary
        toml_content = tomllib.loads(toml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(toml_content))
    except tomllib.TOMLDecodeError as e:
        raise ValueError(f"Invalid TOML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_toml

model_dump_toml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a TOML representation of the model.

Source code in swarmauri_base/TomlMixin.py
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
def model_dump_toml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a TOML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into TOML
    return toml.dumps(filtered_data)

model_validate_yaml classmethod

model_validate_yaml(yaml_data)

Validate a model from a YAML string.

Source code in swarmauri_base/YamlMixin.py
11
12
13
14
15
16
17
18
19
20
21
22
23
@classmethod
def model_validate_yaml(cls, yaml_data: str):
    """Validate a model from a YAML string."""
    try:
        # Parse YAML into a Python dictionary
        yaml_content = yaml.safe_load(yaml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(yaml_content))
    except yaml.YAMLError as e:
        raise ValueError(f"Invalid YAML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_yaml

model_dump_yaml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a YAML representation of the model.

Source code in swarmauri_base/YamlMixin.py
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
def model_dump_yaml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a YAML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into YAML using safe mode
    return yaml.safe_dump(filtered_data, default_flow_style=False)

model_post_init

model_post_init(logger=None)

Assign a logger instance after model initialization.

Source code in swarmauri_base/LoggerMixin.py
23
24
25
26
27
28
def model_post_init(self, logger: Optional[FullUnion[LoggerBase]] = None) -> None:
    """Assign a logger instance after model initialization."""

    # Directly assign the provided FullUnion[LoggerBase] or fallback to the
    # class-level default.
    self.logger = self.logger or logger or self.default_logger

add_allowed_model

add_allowed_model(model)

Add a new model to the list of allowed models.

RAISES DESCRIPTION
ValueError

If the model is already in the allowed models list.

Source code in swarmauri_base/tts/TTSBase.py
27
28
29
30
31
32
33
34
35
36
def add_allowed_model(self, model: str) -> None:
    """
    Add a new model to the list of allowed models.

    Raises:
        ValueError: If the model is already in the allowed models list.
    """
    if model in self.allowed_models:
        raise ValueError(f"Model '{model}' is already allowed.")
    self.allowed_models.append(model)

remove_allowed_model

remove_allowed_model(model)

Remove a model from the list of allowed models.

RAISES DESCRIPTION
ValueError

If the model is not in the allowed models list.

Source code in swarmauri_base/tts/TTSBase.py
38
39
40
41
42
43
44
45
46
47
def remove_allowed_model(self, model: str) -> None:
    """
    Remove a model from the list of allowed models.

    Raises:
        ValueError: If the model is not in the allowed models list.
    """
    if model not in self.allowed_models:
        raise ValueError(f"Model '{model}' is not in the allowed models list.")
    self.allowed_models.remove(model)