Generate speech as a completed audio file.
API ID
azure-speech-neural-ttsOverview
- Input
- Text, one supported voice and an optional speed.
- Output
- A completed audio file.
- Providers
- Azure AI Services
- API compatibility
- OpenAI Audio
Supported features
- Text to speech
Language support
- Input
- Text in a language supported by the selected multilingual voice.
- Output
- Spoken audio; pronunciation depends on the selected voice and input language.
- Choose a language
- Choose one published voice alias through the API. No separate language parameter is exposed.
- Language support varies by voice and does not guarantee pronunciation quality.
- Use Translation when translated content is required.
Sample input → output
InputText, one supported voice and an optional speed.
→Output preview
- Result
- A completed audio file.
Simplified preview based on the published service response contract.
Input requirements
Supported formats
MP3OpusWAVPCM
- API only; unavailable in the Audio workspace and Playground
- Billed by reported characters, which can differ from input length
- Processing can include queue time; immediate streaming is unavailable
- Instructions and ElevenLabs voice settings are unsupported