Audio

Generate Speech with Timestamps

Generate base64-encoded speech with character-level timing for the original and normalized text. See /audio/models for models advertising this endpoint.

post/v1/audio/speech/with-timestamps

Request

  • Base URL: https://gen.pollinations.ai
  • URL: https://gen.pollinations.ai/v1/audio/speech/with-timestamps
  • Auth: HTTP bearer

Request body

model'elevenlabs/eleven-v4' | 'elevenlabs/eleven-v4-turbo' | 'elevenlabs/eleven-v3' | 'elevenlabs/eleven-flash-v2.5' | 'elevenlabs/eleven-multilingual-v2'
inputstring required

Text to synthesize and align.

voicestring

Preset voice name or custom ElevenLabs voice ID.

response_format'mp3' | 'opus' | 'aac' | 'wav' | 'pcm'

Encoding used for audio_base64.

seedinteger

Response

Success - Returns base64 audio and character timings

audio_base64string required

Changes

No recorded changes to this operation across all 1 revision of this API.