There is intentionally no language property in this request. Change only the input text to generate another supported language. Accent, pronunciation, long-form and mixed-language quality vary by language.

Controls and prompt syntax

Qwen3-TTS Base has no documented inline expression-tag vocabulary or SSML contract. Punctuation and wording may influence delivery naturally, but bracketed actions such as [laugh] are not supported syntax and may be spoken literally.

Parameter support

This endpoint does not reject fields it does not recognize. An unrecognized field is accepted, the request returns a normal 200 with audio, and the field is discarded before the request reaches the model. A successful response is therefore never evidence that a field was honored. Use the tables below rather than inferring support from a 200.

Supported

Parameter	Required	Behavior
`model`	yes	`Qwen/Qwen3-TTS-12Hz-1.7B-Base`, case-sensitive
`input`	yes	The text to speak, forwarded unchanged
`voice`	no	Case-sensitive preset name from voice discovery; the discovery-reported default is `Serena`
`stream`	no	Boolean
`stream_format`	no	`sse` or `audio`
`delivery`	no	`stream`, `json`, or `bulk`
`encoding`	no	`binary` or `base64`

input is never inspected or rewritten, so bracketed tokens and markup travel through as literal characters. stream, stream_format, delivery, and encoding select how the audio is returned, not how it is generated. When more than one is present, delivery wins over stream_format, which wins over stream. Set delivery to json (or encoding to base64) to receive the JSON envelope with its format field instead of raw bytes.

Unsupported

Rejected with an error. These fail before any audio is produced, so a client can detect them from the status code and act on it.

Parameter	Result	Error code
`voice` preset name not in the discovery list	`400`	`invalid_voice`
`response_format` outside the advertised set	`400`	`unsupported_format`
`speed` outside `0.25` to `4.0`	`422`	None (schema validation)
Reference-clip `format` outside `mp3`, `opus`, `aac`, `flac`, `wav`, `pcm`	`422`	None (schema validation)
`stream_format` outside `sse`, `audio`	`422`	None (schema validation)
`delivery` outside `stream`, `json`, `bulk`	`422`	None (schema validation)
`voice` matching none of the three accepted shapes	`422`	None (schema validation)

Preset matching is exact and case-sensitive, so a wrong-case name fails with invalid_voice rather than falling back to a default, and the message lists the names that are available. mp3 and wav are always in the set this model advertises through voice discovery, so neither of those two can ever produce unsupported_format.

Convert MP4 or M4A reference audio to WAV before sending it. The three accepted voice shapes are a preset name string, a custom voice object, and a clone reference; a description-based voice prompt sent inside voice matches none of them and fails here.

Accepted and ignored. These return a normal 200 with audio, raise no error, and have no effect. A client cannot detect them from the response, so remove them at the source and never present them as working controls in an interface built on this model.

Parameter	What happens
`voice.clone`	Returns `200` with audio in the default voice. Cloning is not rejected on this model, it is ignored, so a reference clip produces speech that is not the reference speaker and nothing in the response says so.
`language`	Returns `200`, no effect on output
Sampling controls such as `temperature`, `seed`, and `top_p`	Returns `200`, no effect on output
Voice design and description-based voice prompting as top-level fields	Returns `200`, no effect on output
Any other field the endpoint does not define	Returns `200`, no effect on output

This endpoint has no language field, so write the input in the language you want spoken. Voice design and description-based voice prompting have no top-level field either, and the same payload sent inside voice is rejected instead, as the table above shows. Do not send any of these fields, and do not read a 200 as confirmation that one took effect.

Best-effort

Three parameters belong in neither list. They are accepted and carried through the request, but they are not guaranteed to affect the output for this model, so treat them as best effort and verify against this model ID before depending on them. speed is a real, enforced parameter: it must be between 0.25 and 4.0, an out-of-range value fails with 422 before any audio is produced, and omitting it substitutes 1.0 — yet a value inside the range is not guaranteed to change the delivered rate. instructions is accepted as a string and carried through unchanged, and may or may not influence delivery. response_format is a request rather than a guarantee: mp3 and wav are always accepted, and because the only conversion available is a lossless PCM-to-WAV rewrap and never codec transcoding, an accepted request can come back in a container other than the one asked for. Read the container off the response Content-Type, or off the format field of a JSON response, instead of assuming the request was honored.

A custom voice object, sent as {"id": "your-id"} in place of a preset name, is best effort as well, and it differs from a preset name in one way that matters: it deliberately skips preset validation, so an unknown id does not produce the invalid_voice error a mistyped preset name produces. It is accepted and forwarded as-is, and it may select nothing at all or surface as an opaque synthesis failure. Prefer a discovered preset name, and do not present custom voice IDs as a working control in an interface built on this model.

Output and limits

The 12Hz in the model name describes the codec frame rate, not the audio sampling rate. Qwen uses a 24 kHz waveform rate, and the runtime-verified Featherless sample was mono 24 kHz PCM audio in a WAV container. Explicitly request wav for the most predictable result.

Voice discovery currently reports mp3, pcm, and wav as accepted output requests. An accepted selector does not guarantee that exact container: trust the binary response Content-Type or the JSON response format field.

Featherless does not currently publish a stable maximum character count, reference-duration boundary, or output-duration guarantee for this model. Treat those values as unknown, not unlimited, and test realistic input lengths before production.

Streaming

SSE transport is available, but this model currently completes synthesis before audio bytes are delivered. Treat SSE as deferred delivery, not real-time generation; no early-audio or time-to-first-audio guarantee applies. Qwen describes the architecture as streaming-capable, but that model-level capability is not currently exposed by Featherless.

When to use Qwen3-TTS Base

Use the preset workflow for multilingual named-voice speech. Choose another model when speaker matching from a reference clip, explicit speed control, style instructions, inline expression tags, description-based voice design, reusable voice IDs, or live incremental audio are requirements.

Sources

Official Qwen3-TTS Base model card, official Qwen3-TTS repository, official inference interface, and official speech-tokenizer configuration.

Privacy and Logging

API Usage

General