Skip to main content
Typecast logo
  • Category: audio & speech
  • Auth: API_KEY
  • Composio-managed OAuth available? N/A
  • Tools: 7
  • Triggers: 0
  • Slug: TYPECAST
  • Version: 20261014_00

Tools

Slug: TYPECAST_COMPOSE_SPEECHGenerate one audio file from an ordered sequence of speech and pause segments.

Input Parameters

array
required
Ordered speech and pause segments. Include 1-50 segments with at least one tts segment; combined speech text is limited to 2000 characters, and combined pauses to 60 seconds. The top-level audio_format applies to every tts segment.
string ("wav" | "mp3")
Common audio format for every speech segment in the composed file.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: TYPECAST_GENERATE_SPEECHGenerate a complete WAV or MP3 audio file from text using a Typecast voice.

Input Parameters

integer
Optional unsigned 32-bit seed for reproducible generation.
string
required
Text to synthesize (1-2000 characters).
string ("ssfm-v30" | "ssfm-v21")
required
Speech model supported by the selected voice; prefer ssfm-v30 when available.
string
Optional model-specific smart, preset, or ssfm-v21 voice prompt configuration.
integer
Volume from 0 to 200; mutually exclusive with target_lufs.
string
Optional ISO 639-3 language code, such as eng; omit for auto-detection.
string
required
Built-in tc_ voice ID or an owned uc_ custom voice ID.
integer
Pitch adjustment in semitones from -12 to 12.
number
Tempo multiplier from 0.5 to 2.
number
Target loudness from -70 to 0 LUFS; mutually exclusive with volume.
string ("wav" | "mp3")
Format of the generated audio file.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: TYPECAST_GENERATE_SPEECH_WITH_TIMESTAMPSGenerate speech plus word, character, or both alignment timestamp arrays.

Input Parameters

integer
Optional unsigned 32-bit seed for reproducible generation.
string
required
Text to synthesize (1-2000 characters).
string ("ssfm-v30" | "ssfm-v21")
required
Speech model supported by the selected voice; prefer ssfm-v30 when available.
string
Optional model-specific smart, preset, or ssfm-v21 voice prompt configuration.
integer
Volume from 0 to 200; mutually exclusive with target_lufs.
string
Optional ISO 639-3 language code, such as eng; omit for auto-detection.
string
required
Built-in tc_ voice ID or an owned uc_ custom voice ID.
integer
Pitch adjustment in semitones from -12 to 12.
number
Tempo multiplier from 0.5 to 2.
string ("word" | "char")
Return only word or character alignments; omit to return both. Use char for Japanese and Chinese.
number
Target loudness from -70 to 0 LUFS; mutually exclusive with volume.
string ("wav" | "mp3")
Format of the generated audio file.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: TYPECAST_GET_SUBSCRIPTIONGet the connected Typecast API plan, credit usage, concurrency limit, and custom-voice allowance.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: TYPECAST_GET_VOICEGet one voice’s metadata, supported models, and available emotions by voice ID.

Input Parameters

string
required
Typecast tc_ built-in or uc_ custom voice ID to inspect.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: TYPECAST_LIST_VOICESList available built-in and owned custom Typecast voices, optionally filtered by speech model, gender, age, use case, and voice type. Returns each voice ID with the model versions and emotions it supports for use in speech synthesis.

Input Parameters

string ("child" | "teenager" | "young_adult" | "middle_age" | "elder")
Only return voices in this age category.
string ("ssfm-v30" | "ssfm-v21")
Only return voices supporting this speech model.
string ("male" | "female")
Only return voices with this documented gender.
string ("Announcer" | "Anime" | "Audiobook" | "Conversational" | "Documentary" | "E-learning" | "Rapper" | "Game" | "Tiktok/Reels" | "News" | "Podcast" | "Voicemail" | "Ads")
Only return voices matching this Typecast use-case value.
string ("original" | "custom")
Limit results to built-in original voices or owned custom voices.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: TYPECAST_RECOMMEND_VOICESFind and rank Typecast voices that match a natural-language description.

Input Parameters

integer
Number of ranked recommendations to return (1-10). This is not pagination.
string
required
Natural-language description of the desired voice (1-500 characters).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not