Voice generation
Voice generation · 11 endpoints
- Fish Audio: S2.1 Pro text to speechGenerate audio from text, optionally using a reusable private voice owned by the current team.
- Google: Gemini 3.8 Flash-Lite TTSSpeak a text in one of 30 prebuilt voices, or a two-speaker dialogue, with Gemini 3.8 Flash-Lite TTS on Google's own API; the audio returns inline as base64 WAV (24 kHz mono).
- Google: Gemini 3.8 Flash TTSSpeak a text in one of 30 prebuilt voices, or a two-speaker dialogue, with Gemini 3.8 Flash TTS on Google's own API; the audio returns inline as base64 WAV (24 kHz mono).
- Fish Audio: create private voiceCreate a reusable private voice from one or more reference-audio files.
- Fish Audio: delete private voiceDelete one reusable private voice after organization ownership is verified.
- Fish Audio: list managed voicesList the connected Fish account's voices under BYOK, or this treg organization's platform-created voices otherwise.
- Fish Audio: update private voiceUpdate one reusable private voice after organization ownership is verified.
- MiniMax: Speech 2.8 HDGenerate high-definition speech from up to 10,000 characters of text.
- MiniMax: Speech 2.8 TurboGenerate fast, cost-efficient speech from up to 10,000 characters of text.
List voices
- Fish Audio: discover public voicesFind public Fish voices; pass an item's _id to TTS as reference_id. Set licensed=true for Fish's rights-secured subset.
- List available voicesList the current MiniMax system voices and their voice IDs.