Stream generated speech with start and end times for each word and character. The request body matches standard TTS. The response is NDJSON (application/x-ndjson), with one JSON object per line.
Response format:
audio: Base64-encoded WAV or MP3 data. Decode each value separately and join the bytes in order. An empty string carries timestamps only.words / characters: Word or character timestamp arrays. Each entry contains text, start, and end.start / end: Seconds from the start of the generated audio, including tempo, silence removal, and voice effects.Streaming notes. A JSON line may arrive in parts, or several lines may arrive together. Read by newline. Timestamps arrive after the audio through their
endhas been sent; compare them with actual playback position. HTTP 200 alone does not mean completion: a read failure leaves an incomplete result. Only normal response-body completion means success.
/v1/text-to-speech/stream/with-timestampsX-API-KEYstringheaderrequiredAPI key for authentication. You can obtain an API key from the Typecast API Console.
Text-to-speech request parameters
Text to convert to speech. Minimum 1 character, maximum 2000 characters. Credits consumed based on text length. Supports multiple languages including English, Korean, Japanese, and Chinese. Special characters and punctuation are handled automatically.
Voice model to use for speech synthesis.
GET /v3/voices?model=ssfm-v31 and check its supported emotions.ssfm-v31ssfm-v30ssfm-v21Audio output settings including volume (0-200), pitch (-12 to +12 semitones), tempo (0.5x to 2.0x), and format (wav/mp3) for controlling the final audio characteristics
Adjusts the relative volume of the output audio: 0 (completely silent), 50 (half volume), 100 (standard volume, default), 150 (50% louder than standard), 200 (maximum volume, twice as loud as standard).
Since this only scales the existing volume, using volume can amplify the loudness differences between voices if they have different baseline levels. For consistent output across all clips, use target_lufs instead.
target_lufs parameter.Required range: 0 <= x <= 200
Adjusts the pitch in semitones to affect perceived gender and age: -12 (one octave lower, deeper voice), -6 (half octave lower), 0 (original pitch, default), +6 (half octave higher), +12 (one octave higher, higher voice)
Controls speech speed: 0.5 (half speed, very slow and clear), 0.75 (slightly slower than normal), 1.0 (normal speaking speed, default), 1.5 (50% faster than normal), 2.0 (double speed, very fast speech)
Sets the target absolute loudness (LUFS) for the output audio. This normalizes all generated voices to a consistent volume level, regardless of the original source's loudness. Values closer to 0 are louder, while values closer to -70 are quieter.
volume parameter. Use target_lufs for consistent absolute loudness across different clips, or use volume for traditional relative scaling.Output audio format.
WAV format:
MP3 format:
wavmp3Emotion and style settings for the generated speech, including emotion type (happy/sad/angry/normal) and intensity (0.0 to 2.0) to control the emotional expression
Text that comes AFTER the text field in TTSRequest. Provides forward context for emotion inference.
The model analyzes the flow: previous_text → text (synthesized) → next_text
Discriminator field to identify the prompt type. Must be set to "smart" for context-aware emotion inference.
Text that comes BEFORE the text field in TTSRequest. Provides backward context for emotion inference.
The model analyzes the flow: previous_text → text (synthesized) → next_text
Discriminator field to identify the prompt type. Must be set to "preset" for preset-based emotion control.
Emotion preset to apply to the generated speech.
SSFM 3.0 presets: normal, happy, sad, angry, whisper, toneup, tonedown. For SSFM 3.1, check the selected voice's supported emotions.
Check available emotions for each voice in the models field of the GET /v3/voices API response.
normalsadhappyangrywhispertoneuptonedownEmotion preset to apply.
Supported emotions for ssfm-v21: normal, happy, sad, angry
Check available emotions for each voice in the models field of the GET /v3/voices API response.
Language code following ISO 639-3 standard. Case-insensitive (both "ENG" and "eng" are accepted). If not provided, will be auto-detected based on text content.
| Code | Language |
|---|---|
| ARA | Arabic |
| IND | Indonesian |
| POR | Portuguese |
| BEN | Bengali |
| ITA | Italian |
| RON | Romanian |
| BUL | Bulgarian |
| JPN | Japanese |
| RUS | Russian |
| CES | Czech |
| KOR | Korean |
| SLK | Slovak |
| DAN | Danish |
| MSA | Malay |
| SPA | Spanish |
| DEU | German |
| NAN | Min Nan |
| SWE | Swedish |
| ELL | Greek |
| NLD | Dutch |
| TAM | Tamil |
| ENG | English |
| NOR | Norwegian |
| TGL | Tagalog |
| FIN | Finnish |
| PAN | Punjabi |
| THA | Thai |
| FRA | French |
| POL | Polish |
| TUR | Turkish |
| HIN | Hindi |
| UKR | Ukrainian |
| VIE | Vietnamese |
| HRV | Croatian |
| YUE | Cantonese |
| ZHO | Chinese |
| HUN | Hungarian |
| Code | Language |
|---|---|
| ARA | Arabic |
| IND | Indonesian |
| POR | Portuguese |
| BEN | Bengali |
| ITA | Italian |
| RON | Romanian |
| BUL | Bulgarian |
| JPN | Japanese |
| RUS | Russian |
| CES | Czech |
| KOR | Korean |
| SLK | Slovak |
| DAN | Danish |
| MSA | Malay |
| SPA | Spanish |
| DEU | German |
| NAN | Min Nan |
| SWE | Swedish |
| ELL | Greek |
| NLD | Dutch |
| TAM | Tamil |
| ENG | English |
| NOR | Norwegian |
| TGL | Tagalog |
| FIN | Finnish |
| PAN | Punjabi |
| THA | Thai |
| FRA | French |
| POL | Polish |
| TUR | Turkish |
| HIN | Hindi |
| UKR | Ukrainian |
| VIE | Vietnamese |
| HRV | Croatian |
| YUE | Cantonese |
| ZHO | Chinese |
| HUN | Hungarian |
| Code | Language |
|---|---|
| ARA | Arabic |
| IND | Indonesian |
| RON | Romanian |
| BUL | Bulgarian |
| ITA | Italian |
| RUS | Russian |
| CES | Czech |
| JPN | Japanese |
| SLK | Slovak |
| DAN | Danish |
| KOR | Korean |
| SPA | Spanish |
| DEU | German |
| MSA | Malay |
| SWE | Swedish |
| ELL | Greek |
| NLD | Dutch |
| TAM | Tamil |
| ENG | English |
| POL | Polish |
| TGL | Tagalog |
| FIN | Finnish |
| POR | Portuguese |
| UKR | Ukrainian |
| FRA | French |
| HRV | Croatian |
| ZHO | Chinese |
Voice identifier. Two prefixes are supported:
tc_ - Built-in Typecast voices (e.g., tc_60e5426de8b95f1d3000d7b5). See Listing all voices for available IDs.uc_ - Custom voices created via Instant cloning (e.g., uc_64a1b2c3d4e5f6a7b8c9d0e1). Only the owner of a cloned voice can use it.Case-sensitive: must use lowercase prefix.
application/x-ndjson