Free
Text to Speech
Convert text into natural-sounding speech audio.
Natural voicesMP3 downloadNo sign-upFree
Frequently asked questions
Built with Pixeltable
Fact sheet
Last updated
| Modality | Audio |
|---|---|
| Inputs | Text and a voice |
| Outputs | Speech audio |
| Computed column | openai.speech on the text column (model 'tts-1') |
| What updates | A new or changed row recomputes only that row. Unchanged rows stay cached. |
| Canonical doc | Text to speech cookbook |
Runnable sample
import pixeltable as pxt
from pixeltable.functions.openai import speech
TableModel = pxt.model_base()
class Speech(TableModel, name='speech'):
text: pxt.String
voice: pxt.String
speech_audio = speech(input=text, model='tts-1', voice=voice)Related tools
- Audio to Text
Modality: Audio
Computed column: openai.transcriptions on the Audio column (model 'whisper-1')
Docs - Document Summarizer
Modality: Document
Computed column: extract_document_text, then Groq chat_completions for the summary
Docs