ByteDance Seed Speech TTS 2.0

ByteDance Seed Speech TTS 2.0 reads up to 5,000 characters aloud in one of 41 voices and ten languages. $0.03 per 1,000 characters.

Seed Speech TTS 2.0 is ByteDance's speech synthesis model. It reads text aloud in a natural voice, in Chinese, English, Japanese, Spanish, Indonesian, Portuguese, Korean, Italian, German or French. The voice names say which languages they speak: stokie_en is English, felix_zh is Chinese, and a mixed_en_zh voice blends English and Chinese inside one text.

Give the text in text (up to 5,000 characters) and pick one of the 41 preset voices in voice (stokie_en by default). language forces the text to be read as one language; left out, it is detected, Chinese and English mixed included. speed (0.5-2), pitch (-12 to 12 semitones) and volume (0.5-2) shape the voice, and voice_instruction takes a plain sentence about the delivery, such as 'Speak in a warm, cheerful tone' (it is not spoken and does not change the price). output_format is mp3 (the default) or opus.

Inputs: text (required), voice, language, speed, pitch, volume, voice_instruction and output_format. Output: audio, the speech as one file.

Price: $0.03 per 1,000 characters of text, billed on what the run uses and counted to the character: 500 characters cost $0.015, the longest text (5,000 characters) $0.15. The price shown before the run is held on your balance; you are charged exactly what the run cost. It does not clone a voice or follow a reference recording, does not transcribe speech and makes no music or sound effects.

Price: $0.0018 per run. One run with default settings costs $0.0018.

Run ByteDance Seed Speech TTS 2.0 via API

curl -X POST https://api.flymy.ai/api/v1/flymyai/bytedance-seed-speech-tts-2_0/predict \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Hello from FlyMyAI.","voice":"stokie_en"}'

API documentation · Create a free account · Pricing

Related models