Text to Speech API
UnificAlly serves 8 text to speech models from Google and ElevenLabs through one REST API and one API key. Rates start at $0.000105/sec (Gemini 3.8 Flash Lite TTS) or $0.024/1000 characters (Eleven v4 Turbo), depending on how each model bills, and you pay per generation from a prepaid balance with no subscription. Every model below uses the same two calls: POST /v1/tasks to start a job and GET /v1/tasks/{task_id} to fetch the result.
All 8 text to speech models on UnificAlly
| Model | Provider | Starting rate |
|---|---|---|
| Eleven v4 API ElevenLabs #2 on Artificial Analysis TTS arena, audio tags, multi-speaker dialogue, per-request voice cloning. | ElevenLabs | $0.048/1000 characters |
| Eleven v4 Turbo API ElevenLabs #1 on Artificial Analysis TTS arena, ~100 ms median inference, audio tags, dialogue, voice cloning. | ElevenLabs | $0.024/1000 characters |
| Gemini 3.8 Flash Lite TTS API The high-volume Gemini 3.8 voice, Elo 1241 on Artificial Analysis TTS, 100+ languages. | $0.000105/sec | |
| Gemini 3.8 Flash TTS API Elo 1267 on Artificial Analysis TTS, vocal bursts, two-speaker dialogue, 130+ languages. | $0.000158/sec | |
| ElevenLabs API ElevenLabs Eleven v4 and v4 Turbo TTS, multi-voice dialogue, sound effects, vocal isolation, speech-to-text. | ElevenLabs | from $0.024/1000 characters |
| Gemini 3.1 Flash TTS API Inline audio tags, two-speaker dialogue, 30 voices, 70+ languages. | $0.00035/sec | |
| Gemini 2.5 Pro TTS API High-quality narration with 30 voices, dialogue mode, and 70+ languages. | $0.00035/sec | |
| Gemini 2.5 Flash TTS API Fastest, lowest cost per second, with 30 voices and dialogue mode. | $0.000175/sec |
How to call the Text to Speech API
Every model takes the same request: a model ID and an input object. This example uses elevenlabs/text-to-speech; swap in any model ID from the table and the input fields from its model page.
# 1. Start a task
curl -X POST https://api.unifically.com/v1/tasks \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "elevenlabs/text-to-speech",
"input": {
"text": "Hello from UnificAlly.",
"voice": "21m00Tcm4TlvDq8ikWAM"
}
}'
# 2. Read the result with the task_id from step 1
curl https://api.unifically.com/v1/tasks/TASK_ID \
-H "Authorization: Bearer YOUR_API_KEY"Text to Speech API FAQ
- How much does the Text to Speech API cost?
- Each model has its own rate, shown in the table above and on the pricing page. The lowest listed rates right now are $0.000105/sec (Gemini 3.8 Flash Lite TTS) and $0.024/1000 characters (Eleven v4 Turbo). You pay per generation from a prepaid balance: no subscription, no monthly minimum, and the balance does not expire. Failed generations are not charged, and a request with dry_run set to true returns the exact price without running the job.
- How do I call these text to speech models from code?
- Send POST https://api.unifically.com/v1/tasks with your API key, a model ID (for example elevenlabs/text-to-speech) and an input object. The response holds a task_id: poll GET /v1/tasks/{task_id} until the status is completed, or pass a callback_url to receive the result by webhook. The request shape is the same for every model; only the model ID and the input fields change.
- Can I use a custom voice?
- With ElevenLabs text to speech, yes. Its voice field takes either a voice ID from GET /v1/resources/elevenlabs/voices or a list of up to 25 sample URLs of one speaker, which builds a custom voice for that request only; the samples are not kept. The Gemini TTS models use named voices, listed on each model page.
- Can I try the text to speech models before topping up?
- Yes. A new UnificAlly account starts with a $0.50 signup balance, and every model page has a browser playground that runs on it, so you can compare outputs before writing any code.