Synthesize speech audio from text
One step with NVIDIA NIM. We can help you get access.
Get something done
Synthesize speech audio from text
with NVIDIA NIM · Speech & Voice
Use NVIDIA NIM: its NVIDIA NIM Speech TTS API lets you synthesize speech audio from text in a single step (POST /v1/audio/speech). capabilities.work can help you get signed up and connected.
- Can I convert a paragraph of text into a spoken WAV or MP3 file with Magpie-TTS or FastPitch?
- Is it possible to choose the voice and speaking speed when generating text-to-speech audio?
- Which audio formats can synthesized speech be returned in?
Say it to your AI assistant
- Read the text {input} aloud with the {voice} voice on the {model} text-to-speech model.
- Synthesize {input} as {response_format} audio using {model} and voice {voice}.
- Generate speech for {input} with {model} voice {voice}, spoken at {speed} speed.
For your developer
POST /v1/audio/speech in NVIDIA NIM Speech TTS API. Full spec on APIs.io.