ElevenLabs Text-to-Speech Turbo V2.5
Audio
ElevenLabs Text-to-Speech Turbo V2.5
POST
ElevenLabs Text-to-Speech Turbo V2.5
Convert text into speech using the voice of your choice and return the audio.
Request Headers
string
required
Enum value:
application/jsonstring
required
Bearer authentication format: Bearer {{API Key}}.
Request Body
integer
If specified, the system will try to sample deterministically. Repeated requests with the same seed and parameters should return the same result, but full determinism is not guaranteed.Value range: [0, 4294967295]
string
required
The text to convert into speech.
string
required
The voice ID to use.
string
Text that follows the current request text. Used to improve speech continuity when stitching together multiple generations.
string
Language code (ISO 639-1) used for the model and text normalization. If the model does not support this language code, an error will be returned.
string
default:"mp3_44100_128"
The output format of the generated audio. The format is codec_sample_rate_bitrate. The 192 kbps bitrate for MP3 requires a Creator account or above, and the 44.1 kHz sample rate for PCM requires a Pro account or above.Available values:
mp3_22050_32, mp3_24000_48, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, pcm_8000, pcm_16000, pcm_22050, pcm_24000, pcm_32000, pcm_44100, pcm_48000, ulaw_8000, alaw_8000, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192string
Text that precedes the current request text. Used to improve speech continuity when stitching together multiple generations.
boolean
default:false
If true, use the IVC version of the voice instead of the PVC version. This is a temporary workaround for the higher latency of the PVC version.
object
string[]
A list of request_id values for subsequent samples. Used to maintain speech continuity when regenerating samples. Up to 3 request_id values can be provided.Array length: 0 - 3
string[]
A list of request_id values for samples generated before the current generation. Can be used to improve speech continuity. Up to 3 request_id values can be provided.Array length: 0 - 3
string
default:"auto"
Controls text normalization. ‘auto’ lets the system decide, ‘on’ always normalizes, and ‘off’ skips it.Available values:
auto, on, offboolean
default:false
Controls language-specific text normalization for certain supported languages to achieve more natural pronunciation. Warning: This may significantly increase latency. Currently, only Japanese is supported.
object[]
A list of pronunciation dictionary locators (id, version_id) to apply to the text. Applied in order. Up to 3 locators are allowed per request.Array length: 0 - 3
Response Information
Generated audio file Format:binary