Kotoba Text-to-Speech (TTS) Streaming

Kotoba TTS v1.6 accepts text input via SageMaker bidirectional streaming (HTTP/2) at the path /invocations-bidirectional-stream. Standard POST /invocations and batch transform jobs are NOT supported.

A synthesis session is a sequence of JSON events sent over the bidirectional stream:

1. open (required, first event)

   • language (string, optional, default ja): ISO-639-1 language code.
   • speaker_id (string, optional, default default): preset voice identifier. default is always available; additional preset keys (e.g. man-1, woman-1) may also be shipped with the bundle.
   • format (string, optional, default pcm_f32): output audio format. One of pcm_f32 (little-endian float32), pcm_16 (little-endian signed 16-bit), mulaw (8-bit G.711 mu-law), or opus (Ogg/Opus).
   • sample_rate (integer, optional, default 24000): output sample rate in Hz. PCM formats (pcm_f32, pcm_16) accept 8000, 16000, or 24000. mulaw is always emitted at 8000 and opus at 24000, so this field is ignored for them. The negotiated format and sample_rate are echoed on session.created.
   • spk_ref_audio_tokens (optional): speaker reference tokens for the requested voice.

2. response.create (one synthesis turn; repeatable, and may be sent without waiting for the previous response.done — see Pipelining below)

   • text (string, required): the full text to synthesize. The model is one-shot, so the text is not streamed in chunks.
   • response_id (string, optional): client-supplied correlation id; echoed on response.queued / response.created / audio.chunk / response.done. Must be unique among outstanding (active or queued) responses, and reusable once its response.done has been delivered. When omitted the server assigns a UUID.
   • with_timestamps (boolean, optional, default false): when true, audio.chunk events for this response carry alignments records mapping spans of the request text to times in the output audio (see Model output details).
   • max_length (integer, optional): cap on the generated length for this response.

3. response.cancel (optional)

   • response_id (string, optional): cancel the response with this id, whether it is the active response or one still queued. Without it, the active response is cancelled.

Pipelining: while a response is active, additional response.create events are accepted with a response.queued event (carrying the same response.id) and synthesized one at a time in FIFO order. The pending queue is bounded by WS_MAX_PENDING_RESPONSES (default 15); exceeding it yields a non-fatal error (too many queued responses).

Each JSON event must be sent as a UTF-8 text frame. With the SageMaker HTTP/2 SDK, construct RequestPayloadPart with data_type="UTF8" so the payload is forwarded as text.