Text to speech HTTP streaming

post https://api.play.ht/api/v2/tts/stream

Streams the audio bytes with out ultra-fast text-in, audio-out API.

ℹ️
Turbo Model
For our newest PlayDialog-turbo engine powered by Groq, see the Turbo get started guide. It uses the same endpoint but has accepts different voice inputs.

Our HTTP streaming endpoint allows you to send text and receive audio bytes in real-time. You can also use our Python SDK or Nodejs SDK streaming.

Get your Credentials

To use the HTTP API you will need an API Key and a User Id, you can easily generate those, check this guide for a how-to.

Example

For code examples, see the interactive code snippets to the right. The provided examples will return an audio buffer stream that you can use to save locally or stream over the network to a browser, app, or telephony system.

For the complete list of supported parameters, see below.

Body Params

text

string

required

Defaults to Hello Play!

The text to be converted to speech. Limited to 20k characters when voice_engine is set to Play3.0-mini, or 2000 characters otherwise.

voice

string

required

Defaults to s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json

The unique ID for a PlayHT or Cloned Voice.

quality

string

The quality level of the audio. Not supported when voice_engine is set to PlayDialog-turbo.

output_format

string | null

Defaults to wav

The format for the output audio. Note that PlayHT1.0 engine voices and JSON output format only support 'mp3' and 'mulaw'. Currently, PlayDialog-turbo only supports wav.

speed

number

0.1 to 5

Control how fast the generated audio should be. A number greater than 0 and less than or equal to 5.0

sample_rate

number

8000 to 48000

The sample rate of the audio in Hz. Not supported when voice_engine is set to PlayDialog-turbo.

seed

number | null

≥ 0

A seed value for reproducible results. Not supported when voice_engine is set to PlayDialog-turbo.

temperature

number | null

0 to 2

Controls the randomness of the output. Not supported when voice_engine is set to PlayDialog-turbo.

voice_engine

string | null

Defaults to PlayDialog

The voice engine used to synthesize the voice.

emotion

string | null

An emotion to be applied to the speech. Only supported when voice_engine is set to Play3.0-mini, PlayHT2.0 or PlayHT2.0-turbo, and voice uses that engine.

voice_guidance

number | null

1 to 6

A number between 1 and 6. Use lower numbers to reduce how unique your chosen voice will be compared to other voices. Higher numbers will maximize its individuality. Only supported when voice_engine is set to Play3.0-mini, PlayHT2.0 or PlayHT2.0-turbo, and voice uses that engine.

style_guidance

number | null

1 to 30

A number between 1 and 30. Use lower numbers to to reduce how strong your chosen emotion will be. Higher numbers will create a very emotional performance. Only supported when voice_engine is set to Play3.0-mini, PlayHT2.0 or PlayHT2.0-turbo, and voice uses that engine.

text_guidance

number | null

1 to 2

A number between 1 and 2. This number influences how closely the generated speech adheres to the input text. Use lower values to create more fluid speech, but with a higher chance of deviating from the input text. Higher numbers will make the generated speech more accurate to the input text, ensuring that the words spoken align closely with the provided text. Only supported when voice_engine is set to Play3.0-mini or PlayHT2.0, and voice uses that engine.

language

string | null

The language of the voice. Only supported when voice_engine is set to Play3.0-mini or PlayDialog, and voice has 2.0 engine or later. When voice_engine is set to PlayDialog-turbo, only english and arabic are supported.

voice_2

string | null

Only supported when voice_engine is set to PlayDialog. The unique ID for a Voice to be used as second character on multi-turn dialogue generations.

turn_prefix

string | null

Only supported when voice_engine is set to PlayDialog. The prefix to indicate the start of a turn in a multi-turn dialogue with voice.

turn_prefix_2

string | null

Only supported when voice_engine is set to PlayDialog. The prefix to indicate the start of a turn in a multi-turn dialogue with voice_2.

voice_conditioning_seconds

number | null

Only supported when voice_engine is set to PlayDialog. The number of seconds of conditioning to use from the selected voice. Lower values generate audio less similar to the cloned voice, but lead to more model stability and expressiveness. Higher values create output more similar to the cloned voice, but can lead to model instability and reduced expressiveness. Defaults to 20.

voice_conditioning_seconds_2

number | null

Only supported when voice_engine is set to PlayDialog. The number of seconds of conditioning to use from the selected voice_2. Lower values generate audio less similar to the cloned voice, but lead to more model stability and expressiveness. Higher values create output more similar to the cloned voice, but can lead to model instability and reduced expressiveness. Defaults to 20.

Responses

`Content-Type` header of your request and ensure that it is set to a supported media type. You may also need to update your request payload to match the expected media type for the resource you are trying to access.

200A stream of audio bytes.

400The provided payload contains one or more invalid parameters.

401The request was not authorized. Please verity your authorization headers.

403The provided API key's plan does not have access to the requested resource.

429The server has received too many requests from your IP address within a certain time frame and has temporarily blocked your access to this resource. This error is used to prevent abuse of the server. Please refer to the Rate-Limits section for more information.

500An unexpected error occurred.