Text-to-Speech Chirp 3: HD voices are driven by our next generation of LLM models that deliver lifelike and emotionally resonant speech.
Voice Options
| Name | Gender | Demo |
|---|---|---|
| Aoede | Female | |
| Puck | Male | |
| Charon | Male | |
| Kore | Female | |
| Fenrir | Male | |
| Leda | Female | |
| Orus | Male | |
| Zephyr | Female |
Supported output formats
The default response format is LINEAR16, but other formats which are supported include:
- Streaming:
OGG_OPUSandPCM - Non-streaming:
ALAW,MULAW,MP3,OGG_OPUS,PCM
Supported regions
The current preview release supports the following regions: asia-southeast1, global, eu, us
Supported languages
All supported voices and languages are cataloged in the supported voices and languages page.
FAQ
Common questions and their answers:
How do I control pacing and flow to improve the speech output?
You can utilize our troubleshooting tips to improve your text prompt to improve your speech output.
Can I create a voice clone or copy of my own voice?
Yes, we will soon be extending support for cloning your own voice for TTS.
How do I access voices in supported languages?
Voice names follow a specific format, allowing usage across supported languages by specifying the voice uniquely. The format follows \<locale\>-\<model\>-\<voice\>. For example, to use the Kore voice for English (United States) using the Chirp 3: HD voices model, you would specify it as en-US-Chirp3-HD-Kore.