gRPC API Reference#

riva/proto/health.proto#

HealthCheckRequest#

Field	Type	Label	Description
service	string

HealthCheckResponse#

Field	Type	Label	Description
status	HealthCheckResponse.ServingStatus

HealthCheckResponse.ServingStatus#

Name	Number	Description
UNKNOWN	0
SERVING	1
NOT_SERVING	2

Health#

Method Name	Request Type	Response Type	Description
Check	HealthCheckRequest	HealthCheckResponse
Watch	HealthCheckRequest	HealthCheckResponse stream

Top

riva/proto/riva_audio.proto#

AudioEncoding#

AudioEncoding specifies the encoding of the audio bytes in the encapsulating message.

Name	Number	Description
ENCODING_UNSPECIFIED	0	Not specified.
LINEAR_PCM	1	Uncompressed 16-bit signed little-endian samples (Linear PCM).
FLAC	2	`FLAC` (Free Lossless Audio Codec) is the recommended encoding because it is lossless–therefore recognition is not compromised–and requires only about half the bandwidth of `LINEAR16`. `FLAC` stream encoding supports 16-bit and 24-bit samples, however, not all fields in `STREAMINFO` are supported.
MULAW	3	8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
OGGOPUS	4
ALAW	20	8-bit samples that compand 13-bit audio samples using G.711 PCMU/a-law.

Top

riva/proto/riva_common.proto#

RequestId#

Specifies the request ID of the request.

Field	Type	Label	Description
value	string

Top

riva/proto/riva_tts.proto#

RivaSynthesisConfigRequest#

Field	Type	Label	Description
model_name	string		If model is specified only return config for model, otherwise return all configs.

RivaSynthesisConfigResponse#

Field	Type	Label	Description
model_config	RivaSynthesisConfigResponse.Config	repeated

RivaSynthesisConfigResponse.Config#

Field	Type	Label	Description
model_name	string
parameters	RivaSynthesisConfigResponse.Config.ParametersEntry	repeated

RivaSynthesisConfigResponse.Config.ParametersEntry#

Field	Type	Label	Description
key	string
value	string

SynthesizeSpeechRequest#

Field	Type	Description
text	string	Text to be converted to audio. Limited to a maximum of 2,000 characters after normalization, or 500 characters for Chatterbox TTS Multilingual. Requests that exceed this limit are rejected with `Input text is larger than the maximum input length: <size> > 2000` (Chatterbox reports `Input text length (<size>) exceeds maximum allowed length (500). Please reduce the input text size.`). For longer content, split the source text on sentence or paragraph boundaries and send one request per chunk.
language_code	string
encoding	nvidia.riva.AudioEncoding	audio encoding params
sample_rate_hz	int32
voice_name	string	voice params
zero_shot_data	ZeroShotData	Zero Shot model params
custom_dictionary	string	A string containing comma-separated key-value pairs of grapheme and corresponding phoneme separated by double spaces.
custom_configuration	map<string, string>	Key-value pairs forwarded to the model backend for per-request controls. Recognized keys: `flush` — force-flush the streaming text buffer immediately [Magpie only]; `chunk_len_threshold` — minimum buffered character count before a punctuation boundary can flush [Magpie only]; `max_chunk_threshold` — maximum buffered characters before forcing a flush [Magpie only]; `exaggeration_factor` — emotion prosody intensity (Chatterbox only, `0.25`–`2.0`). See Streaming Text Flush Controls and Emotion Exaggeration.
enable_word_time_offsets	bool	If `true`, the response `meta.words` field contains per-word start and end times in milliseconds. If `false`, no word-level timing information is returned. Default is `false`.
id	nvidia.riva.RequestId	The ID to be associated with the request. If provided, this will be returned in the corresponding response.

SynthesizeSpeechResponse#

Field	Type	Description
audio	bytes
meta	SynthesizeSpeechResponseMetadata
id	nvidia.riva.RequestId	The ID associated with the request

SynthesizeSpeechResponseMetadata#

Field	Type	Label	Description
text	string		Currently experimental API addition that returns the input text after preprocessing has been completed as well as the predicted duration for each token. Note: this message is subject to future breaking changes, and potential removal.
processed_text	string
predicted_durations	float	repeated
words	WordTiming	repeated	Per-word timing information. Populated only when `enable_word_time_offsets` is `true` in the request.

WordTiming#

Per-word timing information returned in SynthesizeSpeechResponseMetadata.words when enable_word_time_offsets is true.

Field	Type	Description
word	string	The word as it appears in the normalized (processed) text.
start_time	int32	Start time of the word in milliseconds, relative to the beginning of the audio.
end_time	int32	End time of the word in milliseconds, relative to the beginning of the audio.

ZeroShotData#

Required for Zero Shot model

Field	Type	Description
audio_prompt	bytes	Audio prompt for Zero Shot model. Duration should be between 3 to 10 seconds.
sample_rate_hz	int32	Sample rate for input audio prompt.
encoding	nvidia.riva.AudioEncoding	Encoding of audio prompt. Supported encodings are LINEAR_PCM and OGGOPUS.
quality	int32	The number of times user wants to pass audio through decoder. This ranges between 1-40. Defaults to 20.
transcript	string	Transcript for provided audio prompt.

RivaSpeechSynthesis#

Method Name	Request Type	Response Type	Description
Synthesize	SynthesizeSpeechRequest	SynthesizeSpeechResponse	Used to request text-to-speech from the service. Submit a request containing the desired text and configuration, and receive audio bytes in the requested format.
SynthesizeOnline	SynthesizeSpeechRequest stream	SynthesizeSpeechResponse stream	Used to request text-to-speech returned using stream as it becomes available. Submit a stream of SynthesizeSpeechRequest messages with desired text and configuration, and receive a stream of bytes in the requested format.
GetRivaSynthesisConfig	RivaSynthesisConfigRequest	RivaSynthesisConfigResponse	Enables clients to request the configuration of the current Synthesize service, or a specific model within the service.

Scalar Value Types#

.proto Type	Notes	C++	Java	Python	Go	C#	PHP	Ruby
double		double	double	float	float64	double	float	Float
float		float	float	float	float32	float	float	Float
int32	Uses variable-length encoding. Inefficient for encoding negative numbers – if your field is likely to have negative values, use sint32 instead.	int32	int	int	int32	int	integer	Bignum or Fixnum (as required)
int64	Uses variable-length encoding. Inefficient for encoding negative numbers – if your field is likely to have negative values, use sint64 instead.	int64	long	int/long	int64	long	integer/string	Bignum
uint32	Uses variable-length encoding.	uint32	int	int/long	uint32	uint	integer	Bignum or Fixnum (as required)
uint64	Uses variable-length encoding.	uint64	long	int/long	uint64	ulong	integer/string	Bignum or Fixnum (as required)
sint32	Uses variable-length encoding. Signed int value. These more efficiently encode negative numbers than regular int32s.	int32	int	int	int32	int	integer	Bignum or Fixnum (as required)
sint64	Uses variable-length encoding. Signed int value. These more efficiently encode negative numbers than regular int64s.	int64	long	int/long	int64	long	integer/string	Bignum
fixed32	Always four bytes. More efficient than uint32 if values are often greater than 2^28.	uint32	int	int	uint32	uint	integer	Bignum or Fixnum (as required)
fixed64	Always eight bytes. More efficient than uint64 if values are often greater than 2^56.	uint64	long	int/long	uint64	ulong	integer/string	Bignum
sfixed32	Always four bytes.	int32	int	int	int32	int	integer	Bignum or Fixnum (as required)
sfixed64	Always eight bytes.	int64	long	int/long	int64	long	integer/string	Bignum
bool		bool	boolean	boolean	bool	bool	boolean	TrueClass/FalseClass
string	A string must always contain UTF-8 encoded or 7-bit ASCII text.	string	String	str/unicode	string	string	string	String (UTF-8)
bytes	Can contain any arbitrary sequence of bytes.	string	ByteString	str	[]byte	ByteString	string	String (ASCII-8BIT)