{"stats":{"calls7d":0,"successRate":null,"avgMs":null,"reviews":0,"usefulRate":null},"id":"p/google-ai.voice-gen.gemini-3-8-flash-tts","kind":"provider","name":"google-ai_voice-gen_gemini-3-8-flash-tts","description":"Google: Gemini 3.8 Flash TTS. Speak 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). (Google AI (Gemini API) · Voice generation)","tags":["voice-gen","ai generation","google-ai","gemini-3-8-flash-tts","generate","data"],"method":"POST","path":"/v1/p/google-ai.voice-gen.gemini-3-8-flash-tts","url":"https://toll402.dev/v1/p/google-ai.voice-gen.gemini-3-8-flash-tts","specUrl":"https://toll402.dev/v1/spec/p/google-ai.voice-gen.gemini-3-8-flash-tts","price":"$0.0625","priceUsd":0.0625,"available":true,"inputSchema":{"type":"object","properties":{"contents":{"type":"array","description":"One user turn: {parts: [{text: script}]}. Gemini 3.8 TTS reads `text` as a verbatim transcript: a direction written into it (\"Say cheerfully: ...\") is spoken aloud and billed as audio. Put delivery directions in the part's `speechMetadata.s","examples":[[{"parts":[{"text":"Welcome to treg.","speechMetadata":{"style":"cheerful"}}]}]]},"generationConfig":{"type":"object","properties":{"responseModalities":{"type":"array","description":"Must be [AUDIO].","examples":[["AUDIO"]]},"speechConfig":{"type":"object","description":"Either {voiceConfig: {prebuiltVoiceConfig: {voiceName}}} for one voice, or {multiSpeakerVoiceConfig: {speakerVoiceConfigs: [{speaker, voiceConfig: {prebuiltVoiceConfig: {voiceName}}}]}} for exactly two named speakers. Voices: Zephyr, Puck, ","examples":[{"voiceConfig":{"prebuiltVoiceConfig":{"voiceName":"Kore"}}}]}},"required":["responseModalities","speechConfig"]}},"additionalProperties":true,"required":["contents","generationConfig"]},"example":{"contents":[{"parts":[{"text":"Welcome to treg, the tool catalog for your agents.","speechMetadata":{"style":"cheerful"}}]}],"generationConfig":{"responseModalities":["AUDIO"],"speechConfig":{"voiceConfig":{"prebuiltVoiceConfig":{"voiceName":"Kore"}}}}},"meta":{"provider":"Google AI (Gemini API)","providerSlug":"google-ai","providerDocs":"https://ai.google.dev/gemini-api/docs/image-generation","providerPricing":"https://ai.google.dev/gemini-api/docs/pricing","providerLogo":"https://www.google.com/s2/favicons?domain=ai.google.dev&sz=64","platform":"voice-gen","platformLabel":"Voice generation","category":"AI generation","capability":"voice-gen.gemini-3-8-flash-tts.generate","upstreamMethod":"POST","upstreamPriceUsd":0.05,"pricing":"per_success","pricingNote":"Token-metered at Google's paid-tier rates (through 2026-12-31): input $0.50/M, audio output $9/M, about 25 audio tokens a second ($0.00225 per 10 s). Live 2026-09-30 a 7.1 s line read 22 prompt and 228 audio tokens ($0.002063). A five-minute WAV is about 19 MB of base64 and is spooled.","verified":"2026-09-30","docs":"https://ai.google.dev/gemini-api/docs/speech-generation","calls":0,"successRate":null,"via":"treg"}}