Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Fish Audio TTS API

Deepgram Text-to-Speech (Aura-2, Flux TTS)

OpenAPI 3.1 and AsyncAPI files, llms.txt and Markdown pages. Requests can be kept for training unless each one sets mip_opt_out=true.

Fish Audio TTS API

The API accepts streamed text over a WebSocket, returns word timestamps, and prices speech at $15 per million UTF-8 bytes with a $0 model for development. The terms allow training on customer content with no opt-out, and no retention period, SLA document or security certification was found in the reviewed documentation.

Deepgram Text-to-Speech (Aura-2, Flux TTS)

1. Set mip_opt_out=true on every request if the text mustn't be kept for training.
2. Split Aura-2 REST text under 2,000 characters or expect a 413.
3. Pass model on /v2/speak, where it's required.
4. Strip SSML before sending, since it's removed with an INPUT_MARKUP_STRIPPED warning.
5. Back off exponentially on 429 and keep traffic in one project.

Fish Audio TTS API

1. Send the model header on every request and check its spelling. A missing or unknown value is served and billed as s2.1-pro.
2. Budget by UTF-8 bytes, not characters. Chinese, Japanese and Korean text costs about three bytes a character.
3. Retry 429 and 5xx with exponential backoff. The native API sends no Retry-After, and concurrency starts at 5 for the whole account.
4. Use [bracket] cues on the S2 family. (parenthesis) tags from s1 are read aloud as text.
5. Pass the model explicitly in the JavaScript SDK, because npm release 0.1.0 defaults to s1.