Getting Started — Deeptune

The Deeptune Python library provides convenient access to the Deeptune API from Python.

Installation

1 pip install deeptune

Usage

Instantiate and use the client with the following:

1 from deeptune.client import Deeptune
2 from deeptune.utils import play
3 
4 client = Deeptune(
5     api_key="YOUR_API_KEY",
6 )
7 
8 audio = client.text_to_speech.generate(
9     text="Wow, Deeptune's text to speech API is amazing!",
10     voice="d770a0d0-d7b0-4e52-962f-1a41d252a5f6",
11 )
12 play(audio)

Cloning Voices

There are two different ways you can manage voices with the Deeptune API.

Use Deeptune’s inbuilt voices to upload and manage voices.
Manage voices yourself (eg in your own DB) and clone with generate_from_prompt.

Clone with Voices

Use Deeptune’s inbuilt voices to upload and manage voices.

Clone with Audio Prompt

Manage voices yourself (for example, in your own DB and S3).

Saving the output

Saving manually

The generate and generate_from_prompt endpoints return an iterator of bytes. Make sure to get all of the bytes before writing as demonstrated below.

1 audio = client.text_to_speech.generate(
2     text="Wow, Deeptune's text to speech API is amazing!",
3     voice="d770a0d0-d7b0-4e52-962f-1a41d252a5f6",
4 )
5 audio_bytes = b"".join(audio)
6 
7 # Now, you can save however you'd like
8 with open("output.mp3", "wb") as audio_file:
9     audio_file.write(audio_bytes)

Using built in utils

The also has inbuilt play, save, and stream utility methods. Under the hood, these methods use ffmpeg and mpv to play audio streams.

1 from deeptune.utils import play, save, stream
2 
3 # plays audio using ffmpeg
4 play(audio)
5 # streams audio using mpv
6 stream(audio)
7 # saves audio to file
8 save(audio, "my-file.mp3")

Async Client

The SDK also exports an async client so that you can make non-blocking calls to our API.

1 from deeptune.client import Deeptune
2 from deeptune.utils import play
3 
4 client = AsyncDeeptune(
5     api_key="YOUR_API_KEY",
6 )
7 audio = await client.text_to_speech.generate_from_prompt(
8     text="string",
9     voice="string",
10 )
11 play(audio)

1	from deeptune.client import Deeptune
2	from deeptune.utils import play
3
4	client = Deeptune(
5	api_key="YOUR_API_KEY",
6	)
7
8	audio = client.text_to_speech.generate(
9	text="Wow, Deeptune's text to speech API is amazing!",
10	voice="d770a0d0-d7b0-4e52-962f-1a41d252a5f6",
11	)
12	play(audio)

1	from deeptune.utils import play, save, stream
2
3	# plays audio using ffmpeg
4	play(audio)
5	# streams audio using mpv
6	stream(audio)
7	# saves audio to file
8	save(audio, "my-file.mp3")

1	from deeptune.client import Deeptune
2	from deeptune.utils import play
3
4	client = AsyncDeeptune(
5	api_key="YOUR_API_KEY",
6	)
7	audio = await client.text_to_speech.generate_from_prompt(
8	text="string",
9	voice="string",
10	)
11	play(audio)