Audio

Overview

Available Operations

• speech - Text to speech
• transcribe - Speech to text
• translate - Speech translation

speech

Convert text to speech

Example Usage

from r9s import R9S


with R9S(api_key=os.getenv("R9S_API_KEY",""),) as r9_s:
    res = r9_s.audio.speech(
        model="speech-2.6-turbo",
        input="Hello, welcome to our service!",
        voice="alloy",
        response_format="mp3",
        speed=1)

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description
model	str	:heavy_check_mark:	TTS model name
input	str	:heavy_check_mark:	Text to convert to speech
voice	string (alloy, echo, fable, onyx, nova, shimmer)	:heavy_check_mark:	Voice type
response_format	string (mp3, opus, aac, flac, wav, pcm)	:heavy_minus_sign:	N/A
speed	float	:heavy_minus_sign:	Speech speed
retries	object	:heavy_minus_sign:	Configuration to override the default retry behavior of the client.

Response

CreateAudioSpeechResponse

Errors

Error Type	Status Code	Content Type
errors.BadRequestError	400	application/json
errors.AuthenticationError	401	application/json
errors.PermissionDeniedError	403	application/json
errors.UnprocessableEntityError	422	application/json
errors.RateLimitError	429	application/json
errors.InternalServerError	500	application/json
errors.ServiceUnavailableError	503	application/json
errors.R9SDefaultError	4XX, 5XX	*/*

transcribe

Transcribe speech to text

Example Usage

from r9s import R9S


with R9S(api_key=os.getenv("R9S_API_KEY",""),) as r9_s:

    res = r9_s.audio.transcribe(file={
        "file_name": "example.file",
        "content": open("example.file", "rb"),
    }, model="whisper-1", response_format="json", temperature=0)

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description
file	string	:heavy_check_mark:	Audio file to transcribe
model	str	:heavy_check_mark:	Model name
language	str	:heavy_minus_sign:	Audio language (ISO-639-1 format)
prompt	str	:heavy_minus_sign:	Optional text prompt
response_format	string (json, text, srt, verbose_json, vtt)	:heavy_minus_sign:	N/A
temperature	float	:heavy_minus_sign:	N/A
timestamp_granularities	Array<string (word, segment)>	:heavy_minus_sign:	Timestamp granularity
retries	object	:heavy_minus_sign:	Configuration to override the default retry behavior of the client.

Response

CreateAudioTranscriptionResponse

Errors

Error Type	Status Code	Content Type
errors.BadRequestError	400	application/json
errors.AuthenticationError	401	application/json
errors.PermissionDeniedError	403	application/json
errors.UnprocessableEntityError	422	application/json
errors.RateLimitError	429	application/json
errors.InternalServerError	500	application/json
errors.ServiceUnavailableError	503	application/json
errors.R9SDefaultError	4XX, 5XX	*/*

translate

Translate speech to English text

Example Usage

from r9s import R9S


with R9S(api_key=os.getenv("R9S_API_KEY",""),) as r9_s:

    res = r9_s.audio.translate(file={
        "file_name": "example.file",
        "content": open("example.file", "rb"),
    }, model="whisper-1", response_format="json", temperature=0)

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description
file	string	:heavy_check_mark:	Audio file to translate
model	str	:heavy_check_mark:	Model name
prompt	str	:heavy_minus_sign:	Optional text prompt
response_format	string	:heavy_minus_sign:	N/A
temperature	float	:heavy_minus_sign:	N/A
retries	object	:heavy_minus_sign:	Configuration to override the default retry behavior of the client.

Response

CreateAudioTranslationResponse

Errors

Error Type	Status Code	Content Type
errors.BadRequestError	400	application/json
errors.AuthenticationError	401	application/json
errors.PermissionDeniedError	403	application/json
errors.UnprocessableEntityError	422	application/json
errors.RateLimitError	429	application/json
errors.InternalServerError	500	application/json
errors.ServiceUnavailableError	503	application/json
errors.R9SDefaultError	4XX, 5XX	*/*