Convert text to speech with Gemini 3.8 Flash TTS
Spoken audio (base64) of your text in the chosen voice
$0.16269 per speech (maximum)
The unit rate applies when a result is found. Misses are free when the provider does not bill them; provider-billed misses are charged at cost, without Ahel's margin. Provider-billed failures follow the quoted billing rules. A run that never reaches a provider is not charged. Pending charges stay held until the provider settles.
Quoted before it runs, paid from your prepaid balance. No top-up fee. Pay per call; each call’s price is shown before it runs. The provider ↓
Use Ahel to convert a product announcement for Spotify into speech with Gemini 3.8 Flash TTS. (Ahel task id voice-gen.gemini-3-8-flash-tts.generate.) First call capability_inspect with id "voice-gen.gemini-3-8-flash-tts.generate" for the exact inputs and price, then run_capability with my inputs, and tell me what it cost. If Ahel is not connected yet: Set up Ahel: https://ahel.ai/llms.txt
Provider
1One provider runs this. If it finds nothing, the run ends there. Misses are free when the provider does not bill them; provider-billed misses are charged at cost, without Ahel's margin. Provider-billed failures follow the quoted billing rules. A run that never reaches a provider is not charged. Pending charges stay held until the provider settles. Works counts calls that answered, found or not; New means fewer than 5 calls so far. Rates checked 2026-10-29.
OpenRoutertextvoiceNewunder 5 calls$0.16269/speechonly when foundInputs
2- Textrequired
text · stringWhat to say, up to 150 characters. Returns raw 16-bit PCM, 24 kHz mono (audio/pcm), inline as base64.
- Voicerequired
voice · stringOne of the model's 30 prebuilt voices.
Returns
2audio_base64, media_type. Every row keeps its provider and when it was collected.
- Task id
voice-gen.gemini-3-8-flash-tts.generate