Skip to main content
POST
/
v3
/
elevenlabs-tts-flash-v2
Elevenlabs flash v2 Text to Speech
curl --request POST \
  --url https://api.myrouter.ai/v3/elevenlabs-tts-flash-v2 \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "seed": 123,
  "text": "<string>",
  "voice_id": "<string>",
  "next_text": "<string>",
  "language_code": "<string>",
  "output_format": "<string>",
  "previous_text": "<string>",
  "use_pvc_as_ivc": true,
  "voice_settings": {
    "speed": 123,
    "style": 123,
    "stability": 123,
    "similarity_boost": 123,
    "use_speaker_boost": true
  },
  "next_request_ids": [
    {}
  ],
  "previous_request_ids": [
    {}
  ],
  "apply_text_normalization": "<string>",
  "apply_language_text_normalization": true,
  "pronunciation_dictionary_locators": [
    {
      "version_id": "<string>",
      "pronunciation_dictionary_id": "<string>"
    }
  ]
}
'
Converts text to speech using your chosen voice and returns audio.

​
Request Headers

​
Content-Type
string
required
Enum: application/json
​
Authorization
string
required
Bearer authentication format: Bearer {{API Key}}.

​
Request Body

​
seed
integer
If specified, the system will attempt to sample deterministically. Repeated requests with the same seed and parameters should return the same result, but full determinism is not guaranteed.Range: [0, 4294967295]
​
text
string
required
The text to convert to speech.
​
voice_id
string
required
The voice ID to use.
​
next_text
string
The text that comes after the current request text. Used to improve speech continuity when concatenating multiple generations.
​
language_code
string
Language code (ISO 639-1) used for the model and text normalization. An error will be returned if the model does not support this language code.
​
output_format
string
default:"mp3_44100_128"
Output format for the generated audio. Format is codec_sample_rate_bitrate. The 192kbps bitrate for MP3 requires a Creator or higher account; the 44.1kHz sample rate for PCM requires a Pro or higher account.Possible 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_192
​
previous_text
string
The text that comes before the current request text. Used to improve speech continuity when concatenating multiple generations.
​
use_pvc_as_ivc
boolean
default:false
If true, uses the IVC version of the voice instead of the PVC version. This is a temporary workaround for higher latency with the PVC version.
​
voice_settings
object
​
next_request_ids
array
List of request_ids for subsequent samples. Used to maintain speech continuity when regenerating samples. Up to 3 request_ids can be provided.Array length: 0 - 3
​
previous_request_ids
array
List of request_ids for previously generated samples before the current generation. Can be used to improve speech continuity. Up to 3 request_ids can be provided.Array length: 0 - 3
​
apply_text_normalization
string
default:"auto"
Controls text normalization. ‘auto’ lets the system decide, ‘on’ always normalizes, ‘off’ skips normalization.Possible values: auto, on, off
​
apply_language_text_normalization
boolean
default:false
Controls language-specific text normalization for certain supported languages to achieve more natural pronunciation. Warning: may significantly increase latency. Currently only supports Japanese.
​
pronunciation_dictionary_locators
array
List of pronunciation dictionary locators (id, version_id) to apply to the text. Applied in order. Up to 3 locators per request.Array length: 0 - 3

​
Response

The generated audio file Format: binary